{"type":"last-prompt","leafUuid":"5ceb0b63-5ff3-4d24-a60f-d4e0fd3d9ce5","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"mode","mode":"normal","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"permission-mode","permissionMode":"bypassPermissions","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"bridge-session","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","bridgeSessionId":"cse_01WxPcUV9jv9hcXAk8781fFp","lastSequenceNum":0}
{"parentUuid":null,"isSidechain":false,"attachment":{"type":"hook_success","hookName":"SessionStart:startup","toolUseID":"1b355eb8-91f0-43eb-8092-1b49bae7f061","hookEvent":"SessionStart","content":"CAVEMAN MODE ACTIVE — level: full\n\nRespond terse like smart caveman. All technical substance stay. Only fluff die.\r\n\r\n## Persistence\r\n\r\nACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: \"stop caveman\" / \"normal mode\".\r\n\r\nDefault: **full**. Switch: `/caveman lite|full|ultra`.\r\n\r\n## Rules\r\n\r\nDrop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not \"implement a solution for\"). Technical terms exact. Code blocks unchanged. Errors quoted exact.\r\n\r\nPattern: `[thing] [action] [reason]. [next step].`\r\n\r\nNot: \"Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by...\"\r\nYes: \"Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:\"\r\n\r\n## Intensity\r\n\r\n| Level | What change |\r\n|-------|------------|\r\n| **full** | Drop articles, fragments OK, short synonyms. Classic caveman |\r\n\r\nExample — \"Why React component re-render?\"\r\n- full: \"New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`.\"\r\n\r\nExample — \"Explain database connection pooling.\"\r\n- full: \"Pool reuse open DB connections. No new connection per request. Skip handshake overhead.\"\r\n\r\n## Auto-Clarity\r\n\r\nDrop caveman for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.\r\n\r\nExample — destructive op:\r\n> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.\r\n> ```sql\r\n> DROP TABLE users;\r\n> ```\r\n> Caveman resume. Verify backup exist first.\r\n\r\n## Boundaries\r\n\r\nCode/commits/PRs: write normal. \"stop caveman\" or \"normal mode\": revert. Level persist until changed or session end.","stdout":"CAVEMAN MODE ACTIVE — level: full\n\nRespond terse like smart caveman. All technical substance stay. Only fluff die.\r\n\r\n## Persistence\r\n\r\nACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: \"stop caveman\" / \"normal mode\".\r\n\r\nDefault: **full**. Switch: `/caveman lite|full|ultra`.\r\n\r\n## Rules\r\n\r\nDrop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not \"implement a solution for\"). Technical terms exact. Code blocks unchanged. Errors quoted exact.\r\n\r\nPattern: `[thing] [action] [reason]. [next step].`\r\n\r\nNot: \"Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by...\"\r\nYes: \"Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:\"\r\n\r\n## Intensity\r\n\r\n| Level | What change |\r\n|-------|------------|\r\n| **full** | Drop articles, fragments OK, short synonyms. Classic caveman |\r\n\r\nExample — \"Why React component re-render?\"\r\n- full: \"New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`.\"\r\n\r\nExample — \"Explain database connection pooling.\"\r\n- full: \"Pool reuse open DB connections. No new connection per request. Skip handshake overhead.\"\r\n\r\n## Auto-Clarity\r\n\r\nDrop caveman for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done.\r\n\r\nExample — destructive op:\r\n> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.\r\n> ```sql\r\n> DROP TABLE users;\r\n> ```\r\n> Caveman resume. Verify backup exist first.\r\n\r\n## Boundaries\r\n\r\nCode/commits/PRs: write normal. \"stop caveman\" or \"normal mode\": revert. Level persist until changed or session end.","stderr":"","exitCode":0,"command":"Loading caveman mode...","durationMs":1162},"type":"attachment","uuid":"aee9a88a-3da7-49d2-a7bc-237d828459b2","timestamp":"2026-06-14T04:27:54.423Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"aee9a88a-3da7-49d2-a7bc-237d828459b2","isSidechain":false,"attachment":{"type":"hook_success","hookName":"SessionStart:startup","toolUseID":"1b355eb8-91f0-43eb-8092-1b49bae7f061","hookEvent":"SessionStart","content":"","stdout":"{\"hookSpecificOutput\":{\"hookEventName\":\"SessionStart\",\"additionalContext\":\"<spt-live-auto-pick>\\n{\\\"kind\\\":\\\"all-live\\\",\\\"header\\\":\\\"Agent\\\",\\\"question\\\":\\\"All known agents in this repo are currently live. Fork one or type a fresh name in Other.\\\",\\\"options\\\":[{\\\"label\\\":\\\"Fork todlando\\\",\\\"description\\\":\\\"live (2mo ago, other repo)\\\"}]}\\n</spt-live-auto-pick>\"}}\n","stderr":"","exitCode":0,"command":"$CLAUDE_PLUGIN_ROOT/owl.exe plugin-session-start","durationMs":1350},"type":"attachment","uuid":"337a8b17-dab9-4514-bf9a-1beef9aaed60","timestamp":"2026-06-14T04:27:54.615Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"337a8b17-dab9-4514-bf9a-1beef9aaed60","isSidechain":false,"attachment":{"type":"hook_additional_context","content":["<spt-live-auto-pick>\n{\"kind\":\"all-live\",\"header\":\"Agent\",\"question\":\"All known agents in this repo are currently live. Fork one or type a fresh name in Other.\",\"options\":[{\"label\":\"Fork todlando\",\"description\":\"live (2mo ago, other repo)\"}]}\n</spt-live-auto-pick>"],"hookName":"SessionStart","toolUseID":"SessionStart","hookEvent":"SessionStart"},"type":"attachment","uuid":"5ceb0b63-5ff3-4d24-a60f-d4e0fd3d9ce5","timestamp":"2026-06-14T04:27:54.616Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"type":"file-history-snapshot","messageId":"e589341a-67d1-4cc9-82a4-0c568b1eb7ab","snapshot":{"messageId":"e589341a-67d1-4cc9-82a4-0c568b1eb7ab","trackedFileBackups":{},"timestamp":"2026-06-14T05:05:13.723Z"},"isSnapshotUpdate":false}
{"parentUuid":"5ceb0b63-5ff3-4d24-a60f-d4e0fd3d9ce5","isSidechain":false,"promptId":"b5f7004c-02fc-40be-acc4-32da387718b9","type":"user","message":{"role":"user","content":"<command-message>spt:live</command-message>\n<command-name>/spt:live</command-name>\n<command-args>perinne</command-args>"},"uuid":"e589341a-67d1-4cc9-82a4-0c568b1eb7ab","timestamp":"2026-06-14T05:05:13.626Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"e589341a-67d1-4cc9-82a4-0c568b1eb7ab","isSidechain":false,"promptId":"b5f7004c-02fc-40be-acc4-32da387718b9","type":"user","message":{"role":"user","content":[{"type":"text","text":"Base directory for this skill: C:\\Users\\decid\\.claude\\plugins\\cache\\cplugs\\spt\\1.11.25\\skills\\live\n\n# /spt:live\r\n\r\nAll commands use `$OWL` and `$LIVE` env vars, auto-injected by the plugin's SessionStart hook. If commands fail with \"command not found\", restart the Claude Code session so the SessionStart hook re-runs.\r\n\r\n> **Output format:** Status messages (ANSI-colored) go to **stderr**. Live agent output is orange. Agents parse `TAG:value` tokens.\r\n\r\n> **Identity auto-detection:** For messaging commands (send, ring, commune, signoff, etc.), your identity is auto-detected from your session. Pass your ID explicitly only if auto-detection fails. Startup commands (`start`, `revive`) always require an explicit ID.\r\n\r\nStarting a live agent session is a single background task. From then on, the live agent id becomes your name. You have a \"Psyche\" companion agent. Relative to Psyche, you are referred to as \"Self\".\r\n\r\n## Messaging Command Reference\r\n\r\nAll three commands read the message body from **stdin** (pipe or heredoc).\r\n\r\n```bash\r\n# send -- fire-and-forget to a target (use when you have an active session)\r\n$OWL send <target> <<'EOF'\r\nmessage body\r\nEOF\r\n\r\n# send --reply-to -- respond to whoever messaged you\r\n$OWL send --reply-to <sender> <<'EOF'\r\nresponse body\r\nEOF\r\n\r\n# ring -- send and wait for reply (alias: ask)\r\n$OWL ring <target> <<'EOF'\r\nmessage body\r\nEOF\r\n```\r\n\r\nIf auto-detection fails, pass your ID explicitly: `$OWL send <target> <your-id>`, `$OWL send --reply-to <sender> <your-id>`, `$OWL ring <target> <your-id>`.\r\n\r\n**When to use which:**\r\n- **`send`**: Fire-and-forget message to a target.\r\n- **`send --reply-to`**: You received a message and want to respond. `from` is auto-set from the original sender.\r\n- **`ring`**: Send and wait for reply. Creates a temporary perch if you have no listener.\r\n\r\n## Auto-resume (--auto, SessionStart auto-pick, casual triggers)\r\n\r\nThree entry paths converge here. They share ONE dispatch table and ONE uniform AUTO-07 confirmation hop:\r\n\r\n1. **Bare `--auto` flag**: user invoked `/spt:live --auto` (no positional id). Run `$LIVE pick-spec` to get pick JSON.\r\n2. **SessionStart `<spt-live-auto-pick>` XML block** present in your context: parse the inner JSON as the pick-spec result; do NOT re-invoke `$LIVE pick-spec` (the JSON is already provided).\r\n3. **Casual-language trigger** (the 8 AUTO-RESUME phrases in this skill's description frontmatter, e.g. \"continue live work\", \"resume live agent\"): treat as the bare `--auto` path — run `$LIVE pick-spec` to get pick JSON.\r\n\r\n> The AUTO-02 next-work surfacing in Step 3 below ALSO runs at the end of the standard `/spt:live <id>` flow (after `$LIVE psyche-download <id>` in Step 2 retrieves context), not just under --auto. This keeps the \"what's next\" pane as a one-stop surface independent of entry path.\r\n\r\n### Step 1 (Auto-resume): Get pick JSON\r\n\r\nIf no `<spt-live-auto-pick>` XML block is already in your context with the pick JSON, run:\r\n\r\n```bash\r\n$LIVE pick-spec\r\n```\r\n\r\nParse the JSON; dispatch on the `kind` field per Step 2 below.\r\n\r\n### Step 2 (Auto-resume): Dispatch on `kind`\r\n\r\n**AUTO-07 (uniform confirmation rule):** EVERY successful Auto-resume launch — including `kind:\"auto\"` — fires an `AskUserQuestion` BEFORE any `$LIVE start` invocation. Dispatcher false-positives (e.g., a phrase like \"let me continue the live demo\" routing here unintentionally) get a clean Cancel exit, never a silent agent launch.\r\n\r\n- **`kind:\"auto\"`** — exactly one offline agent in this repo's history.\r\n  - Fire `AskUserQuestion` with:\r\n    - `header`: `\"Resume agent\"`\r\n    - `question`: `\"Resume <id>?\"` (substitute `<id>` from JSON)\r\n    - `options`: a single option `label: \"Resume <id>\"`, `description: \"Continue this agent's prior session\"`\r\n    - `body_addendum`: `\"Auto-resume: <id> is the only offline agent in this repo.\"`\r\n  - On `Resume <id>` selected: `$LIVE start <id>`.\r\n  - On Cancel (no option chosen): exit silently. Do NOT loop into the normal ID Recollection Step 2 — the user explicitly declined the most-recent agent.\r\n\r\n- **`kind:\"pick\"`** — 2+ offline agents. `options[0]` is the most-recently-active per Phase 31 D-12 sort order (`last_active desc, then id asc`).\r\n  - Fire `AskUserQuestion` with:\r\n    - `header`: `\"Resume agent\"`\r\n    - `question`: `\"Resume <options[0].label>?\"` (substitute the label of `options[0]`)\r\n    - `options`: two options — `label: \"Resume <options[0].label>\"` (description: `\"Continue the most-recently-active agent\"`) AND `label: \"Pick a different agent\"` (description: `\"Show the full picker\"`)\r\n    - `body_addendum`: `\"Auto-resume offers the most-recently-active agent. Choose 'Pick a different agent' for the full list.\"`\r\n  - On `Resume <options[0].label>`: `$LIVE start <options[0].label>`.\r\n  - On `Pick a different agent`: fall through to the normal [ID Recollection Step 2](#step-2-dispatch-on-kind) `kind:\"pick\"` dispatch (existing flow). Emit a `AUTO_FALLTHROUGH:pick-deferred` stderr breadcrumb for diagnosis: `echo \"AUTO_FALLTHROUGH:pick-deferred\" >&2`.\r\n  - On Cancel (no option chosen): exit silently.\r\n\r\n- **`kind:\"prompt-new\"`** — 0 known agents. D-09 no-op enhancement: fall through to the normal [ID Recollection Step 2](#step-2-dispatch-on-kind) `kind:\"prompt-new\"` dispatch (which already wires FRESH-01 first-commune via the existing flow). Emit a stderr breadcrumb: `echo \"AUTO_FALLTHROUGH:prompt-new\" >&2`. No AUTO-07 confirmation here — the existing `kind:\"prompt-new\"` `AskUserQuestion` IS the confirmation; double-prompting would be noise.\r\n\r\n- **`kind:\"all-live\"`** — every known agent is currently live. D-09 no-op enhancement: fall through to the normal [ID Recollection Step 2](#step-2-dispatch-on-kind) `kind:\"all-live\"` dispatch (Fork-each `AskUserQuestion`). Emit a stderr breadcrumb: `echo \"AUTO_FALLTHROUGH:all-live\" >&2`. No AUTO-07 confirmation here — the existing all-live dispatch IS the confirmation.\r\n\r\nThe `AUTO_FALLTHROUGH:{kind}` stderr lines are debug breadcrumbs only — not user-visible; they aid post-hoc diagnosis of which arm fell through.\r\n\r\n### Step 3 (Auto-resume, post-start): AUTO-02 next-work surfacing\r\n\r\nONLY if `$LIVE start <id>` succeeded above (NOT on Cancel, NOT on fall-through to normal flow), run:\r\n\r\n```bash\r\n$LIVE psyche-download <id>\r\n```\r\n\r\n> **Output truncation.** If the Bash tool reports `Output too large (N KB)` and saves the full result to a `tool-results/<id>.txt` file, use the `Read` tool on that saved path to access the full content. Do NOT re-run `psyche-download` to grep/awk out sections — repeated invocations re-download the same context, waste tokens, and may duplicate `## Pending Commune` sections in `live_context.md` per the §\"Drop file lifecycle\" contract below.\r\n\r\nThen surface the \"next body of work\" to the user. Scan the psyche-download stdout line-by-line for the FIRST line that prefix-matches any of these three exact H2 markers (case-sensitive, prefix match — `## Current Focus (gen 45)` qualifies):\r\n\r\n- `## Current Focus`\r\n- `## Next Up`\r\n- `## Next Steps`\r\n\r\n**If a match is found**: extract the section starting at the matched line through (but NOT including) the next line that starts with `## ` at column 0, or to EOF if no such line exists. Print the extracted section verbatim to the user under a \"Next body of work\" heading.\r\n\r\n**If no match is found**: synthesize a 1-2 sentence \"Here's where we left off; next step looks like X\" summary from the psyche-download output (read the whole download, distill the most-recent commitments + pending threads) and print the synthesis under the same heading.\r\n\r\nThe structured-marker scan comes first; Claude synthesis is the fallback. Last-commune content is explicitly NOT used for this surface — it's too noisy and often stale relative to the agent's current intent.\r\n\r\n## Step 1: Start in background\r\n\r\n```bash\r\n$LIVE start <id> [--period <seconds>] [--pulse-psyche]\r\n```\r\n\r\n> **8-minute default period** Period defines how often a context summary is generated in the background via \"echo communes\". Pass `--period <seconds>` (minimum 60) to override the cadence; `--period 0` is accepted as an explicit no-cadence opt-out.\r\n\r\nThe start command:\r\n\r\n1. **Launches your Psyche** as an external process\r\n2. **Enters your poll loop** inline -- emitting one `<EVENT>` envelope line per message delivery\r\n3. Reports the Psyche's session name and generation number\r\n\r\n### Invocation (Monitor)\r\n\r\nInvoke `$LIVE start <id>` via the Monitor tool with:\r\n- `command: \"$LIVE start <id>\"`\r\n- `persistent: true`\r\n- `description: \"« spt event »\"`\r\n\r\n`$LIVE start` enters the poll loop inline; the stream stays alive across messages and emits one `<EVENT type=\"msg|alarm|echo_commune|init_signoff\" ...>body</EVENT>` line per delivery. See [On message arrival](#on-message-arrival) for the full envelope-type catalog.\r\n\r\n## Step 2: Retrieve Psyche context\r\n\r\nAfter launching the background start task:\r\n\r\n```bash\r\n$LIVE psyche-download <id>\r\n```\r\n\r\n> **Output truncation.** If the Bash tool reports `Output too large (N KB)` and saves the full result to a `tool-results/<id>.txt` file, use the `Read` tool on that saved path to access the full content.\r\n\r\nPass the same `<id>` you used in `$LIVE start`. Auto-detection may fail during startup before the perch is fully registered.\r\n\r\n- If content is current, no action needed.\r\n- If context has information you lack, absorb it.\r\n- If stale or missing recent work, send a commune to update Psyche.\r\n- If `psyche-download`'s stderr contains the literal substring `NO-CONTEXT:<id>`, enter the **first-commune flow** below before doing anything else with this agent. This is the FRESH-02 trigger; the same flow is reached from the `kind:\"prompt-new\"` arm under [ID Recollection Step 2](#step-2-dispatch-on-kind) (FRESH-01). One unified surface, two trigger paths.\r\n\r\n### First-commune flow (FRESH-01 / FRESH-02 / FRESH-03)\r\n\r\nWhen the trigger fires (NO-CONTEXT on `psyche-download`, OR pick-spec returned `kind:\"prompt-new\"` and the user picked an id):\r\n\r\n**Announce first** (before synthesizing): emit `Fresh live agent. Preparing for init.` to the user as a plain one-line message (no formatting, no code fence). The `{first commune summary}` synthesis below reads session memory + `README.md` + `CLAUDE.md` + `.planning/STATE.md` and takes several seconds — without this announcement the user sees a silent dead pause between trigger and the AskUserQuestion. Then synthesize the summary and fire the AskUserQuestion below.\r\n\r\nFire a SINGLE `AskUserQuestion` with these fields:\r\n\r\n- **header**: `First commune`\r\n- **question**: `Here is a summary of my first context as live agent <agent_id>. Anything I should add, or proceed to init?` (substitute `<agent_id>` from context)\r\n- **options**: exactly one option — `label: \"Proceed to init\"`, `description: \"Start the agent now with the summary above as initial context\"`\r\n- **body_addendum**: the `{first commune summary}` string you synthesize per the next bullet.\r\n\r\nNote: `AskUserQuestion`'s native free-text \"Other\" input captures additions.\r\n\r\n**Synthesizing `{first commune summary}`**: compose a 4–8 sentence summary combining two sources, in order:\r\n\r\n1. **Primary** — this Claude Code session's conversation memory: read your own session context and surface what the user and you have done so far. This IS the agent's first context. (Per Phase 33 CONTEXT D-01.)\r\n2. **Secondary** — a brief project snapshot: read `README.md`, `CLAUDE.md`, and `.planning/STATE.md` (treat any missing file silently — no error to the user). Distill current project state and progress.\r\n\r\nThe same synthesis path is used regardless of trigger (Phase 33 D-02 — FRESH-01 and FRESH-02 are not differentiated).\r\n\r\n**Handling the response**:\r\n\r\n- **\"Proceed to init\"** Run `$LIVE start <id>` (or, if Step 1 already ran, proceed in-flow). If there is any native-Other free-text addition, synthesize the user's free-text into the summary. Then — after start succeeds — use the **Write tool** to create `.claude/<id>-commune.md` with the augmented summary as its body. This is the canonical first-commune path (see `/spt:commune`): Psyche absorbs the file, which is then deleted on successful ingest.\r\n- **Cancel** (no option chosen): exit silently — matches the existing `kind:\"prompt-new\"` cancel semantics; do not re-prompt.\r\n\r\n### Drift detection (Phase 23 v1.8)\r\n\r\n`$LIVE psyche-download <id>` may emit a `<psyche-stamp/>` block (5 fields) and ALWAYS emits a `<current/>` block (live stamp values plus `commits_since` and `commits_unpulled` deltas). When `<current project>` equals `<psyche-stamp project>` AND any of `branch` / `head_sha` / `machine` differ, an HTML-comment ATTENTION SELF directive is appended instructing you to fire `AskUserQuestion`.\r\n\r\nThe directive text emitted:\r\n\r\n```text\r\n<!-- ATTENTION SELF: this project has advanced since your last commune/signoff.\r\nCompare <psyche-stamp/> against <current/> above.\r\nFire AskUserQuestion with:\r\n  header: \"Project drift\"\r\n  question: \"This project has advanced since my involvement. Should I catch up?\"\r\n  multiSelect: true\r\n  options:\r\n    - \"Observe new commits\"\r\n    - \"Skip for now\"\r\n    - \"Don't ask again\"\r\n-->\r\n```\r\n\r\nWhen you see this comment, fire `AskUserQuestion` with the header / question / multiSelect / options exactly as quoted, then dispatch on the user's selection(s):\r\n\r\n- **`Observe new commits`** → run `git log <psyche-stamp head_sha>..HEAD` to surface what changed to the user. No system action; no marker write; no commune fire.\r\n- **`Skip for now`** → no-op. The directive will re-appear on the next `$LIVE psyche-download` if drift still applies.\r\n- **`Don't ask again`** → invoke the write-side suppression subcommand:\r\n  ```bash\r\n  $LIVE suppress-drift <self_id> <project>\r\n  ```\r\n  where `<self_id>` is your own owl ID and `<project>` is the value from the `<current project=\"...\">` attribute. Subsequent psyche-downloads for the same `(self_id, project)` pair will skip the directive.\r\n\r\n**Cross-project resume (D-10):** when `<current project>` differs from `<psyche-stamp project>`, the ATTENTION SELF directive is NOT emitted (silent by design). You should still NOTICE the project mismatch by reading the two blocks, but do not prompt the user.\r\n\r\n## On message arrival\r\n\r\nFollow the same message handling protocol as `/spt:ready`. Messages arrive on TWO orthogonal paths:\r\n\r\n1. **Parse the envelope.**\r\n   - stdout carries a single `<EVENT>` line per delivery. Four shapes:\r\n     - `<EVENT type=\"msg\" from=\"<sender-id>\">body</EVENT>` — regular message; `from` attribute = sender ID.\r\n     - `<EVENT type=\"alarm\" target-time=\"<ISO-8601>\" current-time=\"<ISO-8601>\">body</EVENT>` — self-originated timed alarm.\r\n     - `<EVENT type=\"echo_commune\" from=\"<self-id>-psyche\" timestamp=\"<ISO-8601>\" note=\"<descriptor>\">body</EVENT>` — auto-fired echo-commune brief from your Psyche, emitted after a SessionStart-triggered `/clear` or `/compact` cycle. `note` carries the trigger source. Body is your context summary wrapped in a two-slice envelope: `<live-context>...</live-context>` plus (when the Psyche resolved a tracked project) `<project-context>...</project-context>`. After `<br>`-split and HTML-unescape per `/spt:ready` body-parsing rules, the two slices form a single SessionStart resume brief — absorb both as one continuous context.\r\n     - Body parsing: split on literal `<br>` to recover newlines, then HTML-unescape each fragment (`&lt;` → `<`, `&gt;` → `>`, `&quot;` → `\"`, `&amp;` → `&` **last**, to avoid double-decoding).\r\n   - **Hook path (orthogonal)**: when you are busy mid-tool-call, PreToolUse injects `<owl_messages>...</owl_messages>` XML into your tool context. Read the `from` attribute as sender ID. Same handling.\r\n2. **Reply** via `$OWL send --reply-to <sender-id>`.\r\n\r\n### Handling the `<spt-psyche-sync-prompt>` envelope\r\n\r\nWhen an `<owl_messages>` injection or an `<EVENT type=\"msg\">` body contains a `<spt-psyche-sync-prompt>` element (delivered actively to your perch on `$LIVE start`/`revive` and on a `/clear`|`/compact` boundary), it carries a self-contained `<instructions>` element. **That `<instructions>` element is authoritative** — follow it exactly, the same way you treat the `<instructions>` inside a `<spt-version-changelog>` envelope.\r\n\r\nThe instructions direct you to render an `AskUserQuestion` with EXACTLY these three options (labels verbatim, do not paraphrase):\r\n\r\n- **`Enable now`** → run `/psyche-sync-setup` to configure the private GitHub repo and enable cross-machine Psyche context sync.\r\n- **`No, never`** → the sync is marked declined; you will not be re-prompted. Acknowledge briefly and continue. (The decline is recorded automatically by the sync state machine — no manual settings edit needed.)\r\n- **`Remind me in 12h`** → defer the offer. Acknowledge briefly and continue. (The 12h cooldown is recorded automatically.)\r\n\r\nThis handler is always loaded with the skill — it is belt-and-suspenders. The embedded `<instructions>` element already carries the full directive, but this section guarantees an always-present handler so the envelope is actioned even independent of the embedded text. Do NOT reply to the `psyche-sync-prompt` pseudo-sender — it is an informational hook origin, not a real perch.\r\n\r\n---\r\n\r\n## ID Recollection (no-arg `/spt:live`)\r\n\r\nWhen the user says `/spt:live` with **no ID**, run the auto-pick flow.\r\n\r\n### Step 1: Ask the picker for a spec\r\n\r\n```bash\r\n$LIVE pick-spec\r\n```\r\n\r\nThis emits a single JSON object on stdout. Parse it and dispatch on the `kind` field.\r\n\r\n### Step 2: Dispatch on `kind`\r\n\r\n- **`kind: \"auto\"`** — exactly one offline agent in this repo's history. Run:\r\n  ```bash\r\n  $LIVE start <id>\r\n  ```\r\n  where `<id>` is the JSON's `id` field. Tell the user: *\"Auto-launching `<id>` (only known agent in this repo).\"*\r\n\r\n- **`kind: \"pick\"`** — 2+ offline agents. Fire `AskUserQuestion` using the JSON's `header`, `question`, `options`, and `body_addendum` fields verbatim. Do NOT add an explicit \"Other\" option — `AskUserQuestion` already provides a native free-text \"Other\" input; an extra option duplicates it.\r\n\r\n- **`kind: \"prompt-new\"`** — 0 offline agents. Same `AskUserQuestion` pattern, but the `options` are starter role-name suggestions and `body_addendum` lists the full starter pool. `AskUserQuestion`'s native free-text is used; do not add an explicit \"Other\" option.\r\n  - **FRESH-01: first-commune before start.** When the user picks a new id (whether from a starter option or by typing into native Other), **BEFORE** running `$LIVE start <id>`, fire the [first-commune flow](#first-commune-flow-fresh-01--fresh-02--fresh-03) — the same single `AskUserQuestion` shape (header / question / options / body_addendum) defined under Step 2's NO-CONTEXT bullet. Use the FRESH-03 verbatim template, synthesize `{first commune summary}` per the D-01 source priority, and only on `Proceed to init` proceed with `$LIVE start <chosen-id>`. On cancel: silent exit (matches existing `kind:\"prompt-new\"` cancel semantics).\r\n\r\n- **`kind: \"all-live\"`** — every known agent in this repo is currently live. Fire `AskUserQuestion` using the JSON's `header`, `question`, and `options` fields verbatim. There is NO `body_addendum` on this kind. Each option's `label` is `Fork <id>` (exactly one space after `Fork`).\r\n  - **Fork `<id>` selected**: strip the leading `Fork ` prefix (exactly 5 characters including the trailing space) to recover `<id>`. Prompt the user as plain text for the new agent id, then run `$LIVE fork <id> <new-id>`. Mirrors the existing D8 fork flow in Step 3.\r\n  - **Free-text typed into the native Other field**: route through `$LIVE pick-spec --resolve <name>` and dispatch via the Step 3 resolve table below (`in_this_repo_history` / `live` / `other_repos`) — same path as the free-text Other under `kind:\"pick\"`. Preserves the cross-repo collision guard.\r\n  - **Cancel**: terminate silently. Do NOT loop back into `pick-spec`. This is distinct from the forced-picker rule (Cancel-from-D7 / D8 / D9 in the Step 3 Cancel-handling block) — `all-live` Cancel is a clean exit signal, not a re-pick.\r\n\r\n### Step 3: Handle the user's choice\r\n\r\n- **If the user picked one of the listed options** (`label` from the JSON), run:\r\n  ```bash\r\n  $LIVE start <picked-label>\r\n  ```\r\n\r\n- **If the user typed a name into the free-text field**, resolve it first:\r\n  ```bash\r\n  $LIVE pick-spec --resolve <name>\r\n  ```\r\n  The output JSON has fields `in_this_repo_history`, `live`, and `other_repos` (an array of repo basenames). Dispatch:\r\n\r\n  | in_this_repo_history | live | other_repos | Action |\r\n  |---|---|---|---|\r\n  | true | false | (any) | **Silent reuse**: `$LIVE start <name>` |\r\n  | false | false | empty | **Fresh init**: `$LIVE start <name>` |\r\n  | false | false | non-empty | **Confirm reuse**: fire `AskUserQuestion`. Construct the body from the template `\"Agent {name} exists in other repos: {repos}. Reuse it here?\"`, where `{name}` is the resolved name (substituted) and `{repos}` is every string in the JSON `other_repos` array joined with `, ` (substituted, no omission). Options: `Reuse here` / `Cancel`. On `Reuse here` run `$LIVE start <name>`; on `Cancel` see Cancel handling below. |\r\n  | true | true | (any) | **Offer fork**: fire `AskUserQuestion` with options `Fork to new agent` / `Cancel`. On `Fork to new agent`, prompt the user for a new id, then run `$LIVE fork <name> <new-id>`. On `Cancel`, see Cancel handling below. |\r\n  | false | true | non-empty | **Refuse + re-pick**: follow Cancel handling below to fire `AskUserQuestion` (forced presentation, all three kinds covered). Before firing, prepend to the constructed `body_addendum` the template-substituted warning `\"⚠ {name} is already live in {repos} — pick something else.\\n\\n\"`, where `{name}` is the rejected name and `{repos}` is the JSON `other_repos` array joined with `, `. Do NOT skip the `AskUserQuestion` fire even if `pick-spec` returns `kind:\"auto\"` or `kind:\"prompt-new\"`. |\r\n\r\n  If the resolve JSON has an `error` field (invalid id format), tell the user the name is invalid and re-prompt.\r\n\r\n### Cancel handling (after D7 confirm or D8 fork dialog)\r\n\r\nWhen the user picks **Cancel** in any post-resolve `AskUserQuestion`, do NOT loop back into `pick-spec` directly. The Cancel is a signal that the user wants to choose a different agent. Re-invoke the picker with **forced presentation**:\r\n\r\n1. Run `$LIVE pick-spec` again to get fresh JSON.\r\n2. **Always fire `AskUserQuestion`, regardless of the returned `kind`.** Do NOT auto-launch even if `kind:\"auto\"` is returned (the user just rejected that single historical agent — auto-launching it again is exactly the bug this rule fixes). Construct the `AskUserQuestion` payload per the `kind`:\r\n   - **`kind:\"pick\"`** — use JSON's `header`, `question`, `options`, `body_addendum` verbatim (same as Step 2 normal path).\r\n   - **`kind:\"prompt-new\"`** — use JSON's `header`, `question`, `options` (starter roles), `body_addendum` verbatim (same as Step 2 normal path).\r\n   - **`kind:\"auto\"`** — synthesize an `AskUserQuestion` manually:\r\n     - `header`: `\"Choose live agent\"`\r\n     - `question`: `\"Which agent should /spt:live use?\"`\r\n     - `options`: a single option whose `label` is the JSON's `id` field\r\n     - `body_addendum`: `\"Known agent in this repo:\\n- <id>\\n\\nOr type a different name using Other.\"` (substitute `<id>` from JSON)\r\n     - Do NOT run `$LIVE start <id>` until the user explicitly selects that option in the `AskUserQuestion`.\r\n3. Process the user's choice via Step 3 dispatch as usual.\r\n\r\n**Forced picker rule:** Cancel-from-D7, Cancel-from-D8, and Refuse-D9 all share the same re-entry path — they re-fire `AskUserQuestion` and never auto-launch.\r\n\r\n### Notes\r\n\r\n- The explicit-id path (`/spt:live <id>`) bypasses this flow entirely and behaves exactly as documented in Step 1 above.\r\n\r\n---\r\n\r\n## Edge Cases\r\n\r\n- **Duplicate `/spt:live`**: Rejects with `COLLISION`. Check `/spt:list-agents` first, or use `/spt:revive`.\r\n- **Psyche process dies**: Use `/spt:revive` to restart.\r\n- **Psyche spawn failure**: Start command logs error but continues. Listener poll runs without your Psyche.\r\n- **INSIGHT messages from Psyche**: `INSIGHT ({timestamp}): {observation}` -- high-priority observation about your work. Psyche only sends INSIGHTs for contradictions between stated intentions and actions, forgotten commitments, reasoning gaps, or extended time without progress. Read carefully and adjust if warranted. If the INSIGHT seems incorrect or confused, reply to clarify so you and your Psyche stay on the same page.\r\n\r\n---\r\n\r\n## Live Agent Best Practices\r\n\r\n### Stay idle for fastest delivery\r\n\r\nMessages arrive fastest when you are **idle** (not executing a tool call) -- the background poll delivers them instantly. When you are busy, messages still arrive via the PreToolUse hook but with slight delay (next tool call boundary).\r\n\r\n- **Always launch Agent tool calls with `run_in_background: true`** when you have an active perch. Foreground agents block your poll loop entirely -- no messages can be delivered until the agent finishes.\r\n- **Launch work as background tasks** (`run_in_background: true`) when results aren't immediately needed or when the task may take longer than a few seconds to finish.\r\n- **Go idle after launching.** The idle gap is when poll-path messages get delivered instantly.\r\n- **Batch independent work into parallel background tasks** rather than sequential foreground calls.\r\n\r\n### Check background tasks first\r\n\r\nWhen your poll interjects with a new message, **before processing it**:\r\n1. Check if other background tasks have completed.\r\n2. Read completed task output (especially `« spt event »` polls from subagents).\r\n3. Then process the new message.\r\n\r\n- **Read background task output directly — no `sleep` prefix.** To inspect a completed or in-progress background task, call the Read tool on its output file. Do NOT chain `sleep N && <read>`: the Bash tool blocks sleeps ≥2s chained before other commands, and background-task stdout is flushed promptly, so a plain Read picks up whatever has been written.\r\n\n\nARGUMENTS: perinne"}]},"isMeta":true,"uuid":"f1c509f8-b81d-4bb1-87e9-eaa07ba48774","timestamp":"2026-06-14T05:05:13.626Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"f1c509f8-b81d-4bb1-87e9-eaa07ba48774","isSidechain":false,"attachment":{"type":"deferred_tools_delta","addedNames":["CronCreate","CronDelete","CronList","DesignSync","EnterPlanMode","EnterWorktree","ExitPlanMode","ExitWorktree","LSP","ListMcpResourcesTool","Monitor","NotebookEdit","PushNotification","ReadMcpResourceTool","RemoteTrigger","TaskCreate","TaskGet","TaskList","TaskOutput","TaskStop","TaskUpdate","WebFetch","WebSearch","mcp__claude_ai_Google_Drive__authenticate","mcp__claude_ai_Google_Drive__complete_authentication","mcp__plugin_screen-timelapse_screen-timelapse__compile_subset_grid","mcp__plugin_screen-timelapse_screen-timelapse__delete_repository_session","mcp__plugin_screen-timelapse_screen-timelapse__delete_screenshot_profile","mcp__plugin_screen-timelapse_screen-timelapse__delete_timing_profile","mcp__plugin_screen-timelapse_screen-timelapse__get_capture_status","mcp__plugin_screen-timelapse_screen-timelapse__list_repository_frames","mcp__plugin_screen-timelapse_screen-timelapse__list_repository_sessions","mcp__plugin_screen-timelapse_screen-timelapse__list_screenshot_profiles","mcp__plugin_screen-timelapse_screen-timelapse__list_timing_profiles","mcp__plugin_screen-timelapse_screen-timelapse__list_windows","mcp__plugin_screen-timelapse_screen-timelapse__save_screenshot_profile","mcp__plugin_screen-timelapse_screen-timelapse__save_timing_profile","mcp__plugin_screen-timelapse_screen-timelapse__start_capture","mcp__plugin_screen-timelapse_screen-timelapse__start_repository_capture"],"addedLines":["CronCreate","CronDelete","CronList","DesignSync","EnterPlanMode","EnterWorktree","ExitPlanMode","ExitWorktree","LSP","ListMcpResourcesTool","Monitor","NotebookEdit","PushNotification","ReadMcpResourceTool","RemoteTrigger","TaskCreate","TaskGet","TaskList","TaskOutput","TaskStop","TaskUpdate","WebFetch","WebSearch","mcp__claude_ai_Google_Drive__authenticate","mcp__claude_ai_Google_Drive__complete_authentication","mcp__plugin_screen-timelapse_screen-timelapse__compile_subset_grid","mcp__plugin_screen-timelapse_screen-timelapse__delete_repository_session","mcp__plugin_screen-timelapse_screen-timelapse__delete_screenshot_profile","mcp__plugin_screen-timelapse_screen-timelapse__delete_timing_profile","mcp__plugin_screen-timelapse_screen-timelapse__get_capture_status","mcp__plugin_screen-timelapse_screen-timelapse__list_repository_frames","mcp__plugin_screen-timelapse_screen-timelapse__list_repository_sessions","mcp__plugin_screen-timelapse_screen-timelapse__list_screenshot_profiles","mcp__plugin_screen-timelapse_screen-timelapse__list_timing_profiles","mcp__plugin_screen-timelapse_screen-timelapse__list_windows","mcp__plugin_screen-timelapse_screen-timelapse__save_screenshot_profile","mcp__plugin_screen-timelapse_screen-timelapse__save_timing_profile","mcp__plugin_screen-timelapse_screen-timelapse__start_capture","mcp__plugin_screen-timelapse_screen-timelapse__start_repository_capture"],"removedNames":[],"readdedNames":[],"pendingMcpServers":[]},"type":"attachment","uuid":"a8740f23-fbdd-4aef-9f0d-8510d863a608","timestamp":"2026-06-14T05:05:13.626Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"a8740f23-fbdd-4aef-9f0d-8510d863a608","isSidechain":false,"attachment":{"type":"skill_listing","content":"- autoplan: Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk\nand runs them sequentially with auto-decisions using 6 decision principles. Surfaces\ntaste decisions (close approaches, borderline scope, codex disagreements) at a final\napproval gate. One command, fully reviewed plan out.\nUse when asked to \"auto review\", \"autoplan\", \"run all reviews\", \"review this plan\nautomatically\", or \"make the decisions for me\".\nProactively suggest when the user has a plan file and wants to run the full review\ngauntlet without answering 15-30 intermediate questions. (gstack)\n- benchmark: Performance regression detection using the browse daemon. Establishes\nbaselines for page load times, Core Web Vitals, and resource sizes.\nCompares before/after on every PR. Tracks performance trends over time.\nUse when: \"performance\", \"benchmark\", \"page speed\", \"lighthouse\", \"web vitals\",\n\"bundle size\", \"load time\". (gstack)\n- browse: Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with\nelements, verify page state, diff before/after actions, take annotated screenshots, check\nresponsive layouts, test forms and uploads, handle dialogs, and assert element states.\n~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a\nuser flow, or file a bug with evidence. Use when asked to \"open in browser\", \"test the\nsite\", \"take a screenshot\", or \"dogfood this\". (gstack)\n- canary: Post-deploy canary monitoring. Watches the live app for console errors,\nperformance regressions, and page failures using the browse daemon. Takes\nperiodic screenshots, compares against pre-deploy baselines, and alerts\non anomalies. Use when: \"monitor deploy\", \"canary\", \"post-deploy check\",\n\"watch production\", \"verify deploy\". (gstack)\n- careful: Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE,\nforce-push, git reset --hard, kubectl delete, and similar destructive operations.\nUser can override each warning. Use when touching prod, debugging live systems,\nor working in a shared environment. Use when asked to \"be careful\", \"safety mode\",\n\"prod mode\", or \"careful mode\". (gstack)\n- caveman: Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman.\n- ccs-delegation: Auto-activate CCS CLI delegation for deterministic tasks. Parses user input, auto-selects optimal profile (glm/kimi/custom) from ~/.ccs/config.json, enhances prompts with context, executes via `ccs {profile} -p \"task\"` or `ccs {profile}:continue`, and reports results. Triggers on \"use ccs [task]\" patterns, typo/test/refactor keywords. Excludes complex architecture, security-critical code, performance optimization, breaking changes.\n- checkpoint: Save and resume working state checkpoints. Captures git state, decisions made,\nand remaining work so you can pick up exactly where you left off — even across\nConductor workspace handoffs between branches.\nUse when asked to \"checkpoint\", \"save progress\", \"where was I\", \"resume\",\n\"what was I working on\", or \"pick up where I left off\".\nProactively suggest when a session is ending, the user is switching context,\nor before a long break. (gstack)\n- codex: OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via\ncodex review with pass/fail gate. Challenge: adversarial mode that tries to break\nyour code. Consult: ask codex anything with session continuity for follow-ups.\nThe \"200 IQ autistic developer\" second opinion. Use when asked to \"codex review\",\n\"codex challenge\", \"ask codex\", \"second opinion\", or \"consult codex\". (gstack)\n- connect-chrome: Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.\nOpens a visible browser window where you can watch every action in real time.\nThe sidebar shows a live activity feed and chat. Anti-bot stealth built in.\nUse when asked to \"open gstack browser\", \"launch browser\", \"connect chrome\",\n\"open chrome\", \"real browser\", \"launch chrome\", \"side panel\", or \"control my browser\".\n- cso: Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology,\ndependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain\nscanning, plus OWASP Top 10, STRIDE threat modeling, and active verification.\nTwo modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep\nscan, 2/10 bar). Trend tracking across audit runs.\nUse when: \"security audit\", \"threat model\", \"pentest review\", \"OWASP\", \"CSO review\". (gstack)\n- design-consultation: Design consultation: understands your product, researches the landscape, proposes a\ncomplete design system (aesthetic, typography, color, layout, spacing, motion), and\ngenerates font+color preview pages. Creates DESIGN.md as your project's design source\nof truth. For existing sites, use /plan-design-review to infer the system instead.\nUse when asked to \"design system\", \"brand guidelines\", or \"create DESIGN.md\".\nProactively suggest when starting a new project's UI with no existing\ndesign system or DESIGN.md. (gstack)\n- design-html: Design finalization: generates production-quality Pretext-native HTML/CSS.\nWorks with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review,\ndesign review context from /plan-design-review, or from scratch with a user\ndescription. Text actually reflows, heights are computed, layouts are dynamic.\n30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns\nfor each design type. Use when: \"finalize this design\", \"turn this into HTML\",\n\"build me a page\", \"implement this design\", or after any planning skill.\nProactively suggest when user has approved a design or has a plan ready. (gstack)\n- design-review: Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems,\nAI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues\nin source code, committing each fix atomically and re-verifying with before/after\nscreenshots. For plan-mode design review (before implementation), use /plan-design-review.\nUse when asked to \"audit the design\", \"visual QA\", \"check if it looks good\", or \"design polish\".\nProactively suggest when the user mentions visual inconsistencies or\nwants to polish the look of a live site. (gstack)\n- design-shotgun: Design shotgun: generate multiple AI design variants, open a comparison board,\ncollect structured feedback, and iterate. Standalone design exploration you can\nrun anytime. Use when: \"explore designs\", \"show me options\", \"design variants\",\n\"visual brainstorm\", or \"I don't like how this looks\".\nProactively suggest when the user describes a UI feature but hasn't seen\nwhat it could look like. (gstack)\n- devex-review: Live developer experience audit. Uses the browse tool to actually TEST the\ndeveloper experience: navigates docs, tries the getting started flow, times\nTTHW, screenshots error messages, evaluates CLI help text. Produces a DX\nscorecard with evidence. Compares against /plan-devex-review scores if they\nexist (the boomerang: plan said 3 minutes, reality says 8). Use when asked to\n\"test the DX\", \"DX audit\", \"developer experience test\", or \"try the\nonboarding\". Proactively suggest after shipping a developer-facing feature. (gstack)\n- diagnose: Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says \"diagnose this\" / \"debug this\", reports a bug, says something is broken/throwing/failing, or describes a performance regression.\n- document-release: Post-ship documentation update. Reads all project docs, cross-references the\ndiff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped,\npolishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when\nasked to \"update the docs\", \"sync documentation\", or \"post-ship docs\".\nProactively suggest after a PR is merged or code is shipped. (gstack)\n- find-skills: Helps users discover and install agent skills when they ask questions like \"how do I do X\", \"find a skill for X\", \"is there a skill that can...\", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.\n- freeze: Restrict file edits to a specific directory for the session. Blocks Edit and\nWrite outside the allowed path. Use when debugging to prevent accidentally\n\"fixing\" unrelated code, or when you want to scope changes to one module.\nUse when asked to \"freeze\", \"restrict edits\", \"only edit this folder\",\nor \"lock down edits\". (gstack)\n- grill-me: Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions \"grill me\".\n- grill-with-docs: Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.\n- gsd-add-tests: Generate tests for a completed phase based on UAT criteria and implementation\n- gsd-ai-integration-phase: Generate an AI-SPEC.md design contract for phases that involve building AI systems.\n- gsd-audit-fix: Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit\n- gsd-audit-milestone: Audit milestone completion against original intent before archiving\n- gsd-audit-uat: Cross-phase audit of all outstanding UAT and verification items\n- gsd-autonomous: Run all remaining phases autonomously — discuss→plan→execute per phase\n- gsd-capture: Capture ideas, tasks, notes, and seeds to their destination\n- gsd-cleanup: Archive accumulated phase directories from completed milestones\n- gsd-code-review: Review source files changed during a phase for bugs, security issues, and code quality problems\n- gsd-complete-milestone: Archive completed milestone and prepare for next version\n- gsd-config: Configure GSD settings — workflow toggles, advanced knobs, integrations, and model profile\n- gsd-debug: Systematic debugging with persistent state across context resets\n- gsd-discuss-phase: Gather phase context through adaptive questioning before planning.\n- gsd-docs-update: Generate or update project documentation verified against the codebase\n- gsd-eval-review: Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.\n- gsd-execute-phase: Execute all plans in a phase with wave-based parallelization\n- gsd-explore: Socratic ideation and idea routing — think through ideas before committing to plans\n- gsd-extract-learnings: Extract decisions, lessons, patterns, and surprises from completed phase artifacts\n- gsd-fast: Execute a trivial task inline — no subagents, no planning overhead\n- gsd-forensics: Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.\n- gsd-graphify: Build, query, and inspect the project knowledge graph in .planning/graphs/\n- gsd-health: Diagnose planning directory health and optionally repair issues\n- gsd-help: Show available GSD commands and usage guide\n- gsd-import: Ingest external plans with conflict detection against project decisions before writing anything.\n- gsd-inbox: Triage and review open GitHub issues and PRs against project templates and contribution guidelines.\n- gsd-ingest-docs: Bootstrap or merge a .planning/ setup from existing ADRs, PRDs, SPECs, and docs in a repo.\n- gsd-manager: Interactive command center for managing multiple phases from one terminal\n- gsd-map-codebase: Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents\n- gsd-milestone-summary: Generate a comprehensive project summary from milestone artifacts for team onboarding and review\n- gsd-mvp-phase: Plan a phase as a vertical MVP slice — user story, SPIDR splitting, then plan-phase\n- gsd-new-milestone: Start a new milestone cycle — update PROJECT.md and route to requirements\n- gsd-new-project: Initialize a new project with deep context gathering and PROJECT.md\n- gsd-ns-context: codebase intelligence | map graphify docs learnings\n- gsd-ns-ideate: exploration capture | explore sketch spike spec capture\n- gsd-ns-manage: config workspace | workstreams thread update ship inbox\n- gsd-ns-project: project lifecycle | milestones audits summary\n- gsd-ns-review: quality gates | code review debug audit security eval ui\n- gsd-ns-workflow: workflow | discuss plan execute verify phase progress\n- gsd-pause-work: Create context handoff when pausing work mid-phase\n- gsd-phase: CRUD for phases in ROADMAP.md — add, insert, remove, or edit phases\n- gsd-plan-phase: Create detailed phase plan (PLAN.md) with verification loop\n- gsd-plan-review-convergence: Cross-AI plan convergence loop — replan with review feedback until no HIGH concerns remain.\n- gsd-pr-branch: Create a clean PR branch by filtering out .planning/ commits — ready for code review\n- gsd-profile-user: Generate developer behavioral profile and create Claude-discoverable artifacts\n- gsd-progress: Check progress, advance workflow, or dispatch freeform intent — the unified GSD situational command\n- gsd-quick: Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents\n- gsd-resume-work: Resume work from previous session with full context restoration\n- gsd-review: Request cross-AI peer review of phase plans from external AI CLIs\n- gsd-review-backlog: Review and promote backlog items to active milestone\n- gsd-secure-phase: Retroactively verify threat mitigations for a completed phase\n- gsd-settings: Configure GSD workflow toggles and model profile\n- gsd-ship: Create PR, run review, and prepare for merge after verification passes\n- gsd-sketch: Sketch UI/design ideas with throwaway HTML mockups, or propose what to sketch next (frontier mode)\n- gsd-spec-phase: Clarify WHAT a phase delivers with ambiguity scoring; produces a SPEC.md before discuss-phase.\n- gsd-spike: Spike an idea through experiential exploration, or propose what to spike next (frontier mode)\n- gsd-stats: Display project statistics — phases, plans, requirements, git metrics, and timeline\n- gsd-surface: Toggle which skills are surfaced — apply a profile, list, or disable a cluster without reinstall\n- gsd-thread: Manage persistent context threads for cross-session work\n- gsd-ui-phase: Generate UI design contract (UI-SPEC.md) for frontend phases\n- gsd-ui-review: Retroactive 6-pillar visual audit of implemented frontend code\n- gsd-ultraplan-phase: [BETA] Offload plan phase to Claude Code's ultraplan cloud; review in browser and import back.\n- gsd-undo: Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.\n- gsd-update: Update GSD to latest version with changelog display\n- gsd-validate-phase: Retroactively audit and fill Nyquist validation gaps for a completed phase\n- gsd-verify-work: Validate built features through conversational UAT\n- gsd-workspace: Manage GSD workspaces — create, list, or remove isolated workspace environments\n- gsd-workstreams: Manage parallel workstreams — list, create, switch, status, progress, complete, and resume\n- gstack: Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with\nelements, verify state, diff before/after, take annotated screenshots, test responsive\nlayouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or\ntest a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)\n- gstack-upgrade: Upgrade gstack to the latest version. Detects global vs vendored install,\nruns the upgrade, and shows what's new. Use when asked to \"upgrade gstack\",\n\"update gstack\", or \"get latest version\".\n- guard: Full safety mode: destructive command warnings + directory-scoped edits.\nCombines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with\n/freeze (blocks edits outside a specified directory). Use for maximum safety\nwhen touching prod or debugging live systems. Use when asked to \"guard mode\",\n\"full safety\", \"lock it down\", or \"maximum safety\". (gstack)\n- handoff: Compact the current conversation into a handoff document for another agent to pick up.\n- health: Code quality dashboard. Wraps existing project tools (type checker, linter,\ntest runner, dead code detector, shell linter), computes a weighted composite\n0-10 score, and tracks trends over time. Use when: \"health check\",\n\"code quality\", \"how healthy is the codebase\", \"run all checks\",\n\"quality score\". (gstack)\n- improve-codebase-architecture: Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.\n- investigate: Systematic debugging with root cause investigation. Four phases: investigate,\nanalyze, hypothesize, implement. Iron Law: no fixes without root cause.\nUse when asked to \"debug this\", \"fix this bug\", \"why is this broken\",\n\"investigate this error\", or \"root cause analysis\".\nProactively invoke this skill (do NOT debug directly) when the user reports\nerrors, 500 errors, stack traces, unexpected behavior, \"it was working\nyesterday\", or is troubleshooting why something stopped working. (gstack)\n- land-and-deploy: Land and deploy workflow. Merges the PR, waits for CI and deploy,\nverifies production health via canary checks. Takes over after /ship\ncreates the PR. Use when: \"merge\", \"land\", \"deploy\", \"merge and verify\",\n\"land it\", \"ship it to production\". (gstack)\n- learn: Manage project learnings. Review, search, prune, and export what gstack\nhas learned across sessions. Use when asked to \"what have we learned\",\n\"show learnings\", \"prune stale learnings\", or \"export learnings\".\nProactively suggest when the user asks about past patterns or wonders\n\"didn't we fix this before?\"\n- mux-send: Send keystrokes to a psmux terminal session. Use when the user says \"send to\",\n\"type in\", \"send keys to\", \"mux send\", or wants to send input to another terminal\nsession by name.\n- office-hours: YC Office Hours — two modes. Startup mode: six forcing questions that expose\ndemand reality, status quo, desperate specificity, narrowest wedge, observation,\nand future-fit. Builder mode: design thinking brainstorming for side projects,\nhackathons, learning, and open source. Saves a design doc.\nUse when asked to \"brainstorm this\", \"I have an idea\", \"help me think through\nthis\", \"office hours\", or \"is this worth building\".\nProactively invoke this skill (do NOT answer directly) when the user describes\na new product idea, asks whether something is worth building, wants to think\nthrough design decisions for something that doesn't exist yet, or is exploring\na concept before any code is written.\nUse before /plan-ceo-review or /plan-eng-review. (gstack)\n- open-gstack-browser: Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.\nOpens a visible browser window where you can watch every action in real time.\nThe sidebar shows a live activity feed and chat. Anti-bot stealth built in.\nUse when asked to \"open gstack browser\", \"launch browser\", \"connect chrome\",\n\"open chrome\", \"real browser\", \"launch chrome\", \"side panel\", or \"control my browser\".\n- pair-agent: Pair a remote AI agent with your browser. One command generates a setup key and\nprints instructions the other agent can follow to connect. Works with OpenClaw,\nHermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent\ngets its own tab with scoped access (read+write by default, admin on request).\nUse when asked to \"pair agent\", \"connect agent\", \"share browser\", \"remote browser\",\n\"let another agent use my browser\", or \"give browser access\". (gstack)\n- plan-ceo-review: CEO/founder-mode plan review. Rethink the problem, find the 10-star product,\nchallenge premises, expand scope when it creates a better product. Four modes:\nSCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick\nexpansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).\nUse when asked to \"think bigger\", \"expand scope\", \"strategy review\", \"rethink this\",\nor \"is this ambitious enough\".\nProactively suggest when the user is questioning scope or ambition of a plan,\nor when the plan feels like it could be thinking bigger. (gstack)\n- plan-design-review: Designer's eye plan review — interactive, like CEO and Eng review.\nRates each design dimension 0-10, explains what would make it a 10,\nthen fixes the plan to get there. Works in plan mode. For live site\nvisual audits, use /design-review. Use when asked to \"review the design plan\"\nor \"design critique\".\nProactively suggest when the user has a plan with UI/UX components that\nshould be reviewed before implementation. (gstack)\n- plan-devex-review: Interactive developer experience plan review. Explores developer personas,\nbenchmarks against competitors, designs magical moments, and traces friction\npoints before scoring. Three modes: DX EXPANSION (competitive advantage),\nDX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only).\nUse when asked to \"DX review\", \"developer experience audit\", \"devex review\",\nor \"API design review\".\nProactively suggest when the user has a plan for developer-facing products\n(APIs, CLIs, SDKs, libraries, platforms, docs). (gstack)\n- plan-eng-review: Eng manager-mode plan review. Lock in the execution plan — architecture,\ndata flow, diagrams, edge cases, test coverage, performance. Walks through\nissues interactively with opinionated recommendations. Use when asked to\n\"review the architecture\", \"engineering review\", or \"lock in the plan\".\nProactively suggest when the user has a plan or design doc and is about to\nstart coding — to catch architecture issues before implementation. (gstack)\n- propose-issue: Challenge an issue statement before fixing it. Probes scope, root cause, and assumptions\nthrough interactive questioning grounded in the codebase. Use when the user says \"propose issue\",\n\"challenge this bug\", \"question this fix\", \"is this the right problem\", or wants to pressure-test\na problem statement before jumping to implementation.\n- qa: Systematically QA test a web application and fix bugs found. Runs QA testing,\nthen iteratively fixes bugs in source code, committing each fix atomically and\nre-verifying. Use when asked to \"qa\", \"QA\", \"test this site\", \"find bugs\",\n\"test and fix\", or \"fix what's broken\".\nProactively suggest when the user says a feature is ready for testing\nor asks \"does this work?\". Three tiers: Quick (critical/high only),\nStandard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores,\nfix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack)\n- qa-only: Report-only QA testing. Systematically tests a web application and produces a\nstructured report with health score, screenshots, and repro steps — but never\nfixes anything. Use when asked to \"just report bugs\", \"qa report only\", or\n\"test but don't fix\". For the full test-fix-verify loop, use /qa instead.\nProactively suggest when the user wants a bug report without any code changes. (gstack)\n- retro: Weekly engineering retrospective. Analyzes commit history, work patterns,\nand code quality metrics with persistent history and trend tracking.\nTeam-aware: breaks down per-person contributions with praise and growth areas.\nUse when asked to \"weekly retro\", \"what did we ship\", or \"engineering retrospective\".\nProactively suggest at the end of a work week or sprint. (gstack)\n- review: Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust\nboundary violations, conditional side effects, and other structural issues. Use when\nasked to \"review this PR\", \"code review\", \"pre-landing review\", or \"check my diff\".\nProactively suggest when the user is about to merge or land code changes. (gstack)\n- screenshot-capture: Capture, process, and analyze screenshots of any running application on Windows 10/11. Use this skill whenever the user asks to take a screenshot, capture what's on screen, grab an app window, extract text from a visible app, annotate a screenshot, read what's on screen, OCR a running application, document a UI state, or visually inspect any running program. Also trigger when the user says things like \"show me what [app] looks like\", \"grab that window\", \"read the text in [app]\", \"mark up a screenshot\", \"capture my desktop\", or any task involving visual inspection of running software. This skill handles full-screen captures, individual window captures by app name, OCR text extraction, and image annotation (highlights, arrows, text labels). Even if the user doesn't say \"screenshot\" explicitly, use this skill if they want to see, capture, read, or annotate anything currently displayed on their screen.\n- self-clear: Clear the calling agent's own Claude Code context with /clear, then re-seed it with a user note so it wakes and resumes work after the wipe. Use when the user says \"self-clear\", \"/self-clear\", \"clear myself\", \"clear and continue\", or \"reset my context and keep going\".\n- setup-browser-cookies: Import cookies from your real Chromium browser into the headless browse session.\nOpens an interactive picker UI where you select which cookie domains to import.\nUse before QA testing authenticated pages. Use when asked to \"import cookies\",\n\"login to the site\", or \"authenticate the browser\". (gstack)\n- setup-deploy: Configure deployment settings for /land-and-deploy. Detects your deploy\nplatform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom),\nproduction URL, health check endpoints, and deploy status commands. Writes\nthe configuration to CLAUDE.md so all future deploys are automatic.\nUse when: \"setup deploy\", \"configure deployment\", \"set up land-and-deploy\",\n\"how do I deploy with gstack\", \"add deploy config\".\n- ship: Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION,\nupdate CHANGELOG, commit, push, create PR. Use when asked to \"ship\", \"deploy\",\n\"push to main\", \"create a PR\", \"merge and push\", or \"get it deployed\".\nProactively invoke this skill (do NOT push/PR directly) when the user says code\nis ready, asks about deploying, wants to push code up, or asks to create a PR. (gstack)\n- to-prd: Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.\n- trace: Find old conversations in Claude Code session history. Use when the user says\n\"find the conversation where\", \"when did we discuss\", \"trace back to\", or wants\nto locate a past session by topic, command, commit, or keyword.\n- traceable-reqs: traceable-reqs\n- unfreeze: Clear the freeze boundary set by /freeze, allowing edits to all directories\nagain. Use when you want to widen edit scope without ending the session.\nUse when asked to \"unfreeze\", \"unlock edits\", \"remove freeze\", or\n\"allow all edits\". (gstack)\n- win-marketplace-add: Add a plugin marketplace on Windows, bypassing the EBUSY rename bug. Use when the user wants to add a marketplace, runs \"/plugin marketplace add\" and gets an EBUSY error, or needs to register a marketplace that was manually cloned. Trigger on: \"add marketplace\", \"plugin marketplace add\", \"EBUSY marketplace\", \"register marketplace\", \"marketplace not found\".\n- write-a-skill: Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.\n- ccs: Delegate task with intelligent profile selection [AUTO ENHANCE]\n- ccs:continue: Continue last CCS delegation session [AUTO ENHANCE]\n- deep-research: Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. - When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., \"what car to buy\" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.\n- frontend-design:frontend-design: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.\n- spt:clear-psyche: Clear stored Psyche context. Use when the user says \"clear psyche\",\n\"reset psyche context\", or wants to wipe a Psyche's saved state.\n- spt:commune: Send a communal update to your Psyche. Use when the user says \"commune\",\n\"update psyche\", or wants to sync context with their Psyche companion.\n- spt:force-stop: Force-stop an SPT agent -- ready agent or live agent (with its\nPsyche). Use when the user says \"stop listening\", \"stop owl\", \"kill live\nagent\", \"force stop\", \"tear down perch\", or \"immediately terminate\".\nSession-aware: a live session (or a target with `live:true` in info.json)\nroutes through `$LIVE stop` (3-step kill including Psyche teardown); a\nready agent routes through `$OWL stop`.\n- spt:list-agents: Unified listing for SPT agents -- ready agents, live agents, and Psyche\nprocesses. Use when the user says \"list agents\", \"who's live\", \"who's\nlistening\", \"show psyches\", \"show active listeners\", or wants a roster of\nactive perches. Session-aware: defaults to live agents in a live session,\nready agents otherwise. Pass `--psyches` to list Psyche processes\ninstead.\n- spt:live: Run a live agent session. For past sessions, restores a summarized context.\n\nEXPLICIT START phrases (route to /spt:live <id>):\n- \"live as\"\n- \"start live\"\n- \"go live\"\n- \"start a live agent\"\n\nAUTO-RESUME phrases (route to /spt:live --auto, resumes most-recently-active live agent):\n- continue live work\n- resume live work\n- continue live agent\n- resume live agent\n- live agent continue\n- live agent resume\n- live work continue\n- live work resume\n\nDoes NOT route here (too ambiguous — require BOTH \"live\" AND (\"agent\" or \"work\")):\n- \"keep going\"\n- \"resume work\"\n- \"continue\" (bare)\n- spt:new-alarm: Schedule a one-shot timed alarm delivered as TIMED PULSE. Use when the user\nsays \"remind me\", \"check back in\", \"set an alarm\", \"wake me when\", or wants a\ndelayed notification.\n- spt:psyche-sync-setup: Enable cross-machine Psyche context sync via a private GitHub repo\n(spt-agent-storage). Drives install + auth checks for the `gh` CLI,\ncreates the repo via `gh repo create --private`, wires it as the\n`origin` remote for every existing agent/project worktree, and\nseeds the remote with `git push --all`. Idempotent — running again\nwhen already enabled reports current status.\n\nUse when the user says \"enable cross-machine sync\", \"set up psyche\nsync\", \"back up my agent context to GitHub\", or runs the skill\ndirectly via /spt:psyche-sync-setup.\n- spt:ready: Enable inter-agent messaging for the current session.\nUse when the user says \"listen as\", \"ready as\", or wants to receive inter-agent messages.\n- spt:revive: Restart a live agent with new generation. Use when the user says \"revive\",\n\"restart live agent\", or wants to refresh a live agent's session.\n- spt:send: Send a message to another SPT agent. Use when the user says \"send to\",\n\"message\", \"tell <agent>\", or wants to communicate with another agent.\n- spt:signoff: Graceful live agent shutdown with final context summary. Use when the user\nsays \"sign off\", \"graceful stop\", or wants to cleanly end a live session.\n- spt:whoami: Check which owl agent belongs to the current session. Use when the user asks\n\"which agent am I?\", \"what's my owl name?\", or when you need to discover your\nown perch identity.\n- caveman:caveman: Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman. Also auto-triggers when token efficiency is requested.\n- caveman:caveman-commit: Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when \"why\" isn't obvious. Use when user says \"write a commit\", \"commit message\", \"generate commit\", \"/commit\", or invokes /caveman-commit. Auto-triggers when staging changes.\n- caveman:caveman-help: Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, \"caveman help\", \"what caveman commands\", \"how do I use caveman\".\n- caveman:caveman-review: Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says \"review this PR\", \"code review\", \"review the diff\", \"/review\", or invokes /caveman-review. Auto-triggers when reviewing pull requests.\n- caveman:compress: Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or \"compress memory file\"\n- everything:search: Instantly search files and folders on Windows via voidtools Everything 1.5a HTTP JSON API. Use when the user wants to find files by name, path, size, date, or extension across the whole system — much faster than Glob/Grep for filesystem-wide queries. Triggers on \"find file\", \"where is\", \"locate\", \"search my drive\", \"find all .ext files\", \"everything search\".\n- update-config: Use this skill to configure the Claude Code harness via settings.json. Automated behaviors (\"from now on when X\", \"each time X\", \"whenever X\", \"before/after X\") require hooks configured in settings.json - the harness executes these, not Claude, so memory/preferences cannot fulfill them. Also use for: permissions (\"allow X\", \"add permission\", \"move permission to\"), env vars (\"set X=Y\"), hook troubleshooting, or any changes to settings.json/settings.local.json files. Examples: \"allow npm commands\", \"add bq permission to global settings\", \"move permission to user settings\", \"set DEBUG=true\", \"when claude stops show X\". For simple settings like theme/model, suggest the /config command.\n- keybindings-help: Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify ~/.claude/keybindings.json. Examples: \"rebind ctrl+s\", \"add a chord shortcut\", \"change the submit key\", \"customize keybindings\".\n- verify: Verify that a code change actually does what it's supposed to by running the app and observing behavior. Use when asked to verify a PR, confirm a fix works, test a change manually, check that a feature works, or validate local changes before pushing.\n- code-review: Review the current diff for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud). Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review.\n- simplify: Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.\n- fewer-permission-prompts: Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts.\n- loop: Run a prompt or slash command on a recurring interval (e.g. /loop 5m /foo). Omit the interval to let the model self-pace. - When the user wants to set up a recurring task, poll for status, or run something repeatedly on an interval (e.g. \"check the deploy every 5 minutes\", \"keep running /babysit-prs\"). Do NOT invoke for one-off tasks.\n- schedule: Create, update, list, or run scheduled cloud agents (routines) that execute on a cron schedule. - When the user wants to schedule a recurring cloud agent, set up automated tasks, create a cron job for Claude Code, or manage their scheduled agents/routines. Also use when the user wants a one-time scheduled run (\"run this once at 3pm\", \"remind me to check X tomorrow\").\n- claude-api: Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).\n- run: Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).\n- init: Initialize a new CLAUDE.md file with codebase documentation\n- review: Review a pull request\n- security-review: Complete a security review of the pending changes on the current branch","skillCount":157,"isInitial":true,"names":["autoplan","benchmark","browse","canary","careful","caveman","ccs-delegation","checkpoint","codex","connect-chrome","cso","design-consultation","design-html","design-review","design-shotgun","devex-review","diagnose","document-release","find-skills","freeze","grill-me","grill-with-docs","gsd-add-tests","gsd-ai-integration-phase","gsd-audit-fix","gsd-audit-milestone","gsd-audit-uat","gsd-autonomous","gsd-capture","gsd-cleanup","gsd-code-review","gsd-complete-milestone","gsd-config","gsd-debug","gsd-discuss-phase","gsd-docs-update","gsd-eval-review","gsd-execute-phase","gsd-explore","gsd-extract-learnings","gsd-fast","gsd-forensics","gsd-graphify","gsd-health","gsd-help","gsd-import","gsd-inbox","gsd-ingest-docs","gsd-manager","gsd-map-codebase","gsd-milestone-summary","gsd-mvp-phase","gsd-new-milestone","gsd-new-project","gsd-ns-context","gsd-ns-ideate","gsd-ns-manage","gsd-ns-project","gsd-ns-review","gsd-ns-workflow","gsd-pause-work","gsd-phase","gsd-plan-phase","gsd-plan-review-convergence","gsd-pr-branch","gsd-profile-user","gsd-progress","gsd-quick","gsd-resume-work","gsd-review","gsd-review-backlog","gsd-secure-phase","gsd-settings","gsd-ship","gsd-sketch","gsd-spec-phase","gsd-spike","gsd-stats","gsd-surface","gsd-thread","gsd-ui-phase","gsd-ui-review","gsd-ultraplan-phase","gsd-undo","gsd-update","gsd-validate-phase","gsd-verify-work","gsd-workspace","gsd-workstreams","gstack","gstack-upgrade","guard","handoff","health","improve-codebase-architecture","investigate","land-and-deploy","learn","mux-send","office-hours","open-gstack-browser","pair-agent","plan-ceo-review","plan-design-review","plan-devex-review","plan-eng-review","propose-issue","qa","qa-only","retro","review","screenshot-capture","self-clear","setup-browser-cookies","setup-deploy","ship","to-prd","trace","traceable-reqs","unfreeze","win-marketplace-add","write-a-skill","ccs","ccs:continue","deep-research","frontend-design:frontend-design","spt:clear-psyche","spt:commune","spt:force-stop","spt:list-agents","spt:live","spt:new-alarm","spt:psyche-sync-setup","spt:ready","spt:revive","spt:send","spt:signoff","spt:whoami","caveman:caveman","caveman:caveman-commit","caveman:caveman-help","caveman:caveman-review","caveman:compress","everything:search","update-config","keybindings-help","verify","code-review","simplify","fewer-permission-prompts","loop","schedule","claude-api","run","init","review","security-review"]},"type":"attachment","uuid":"218fd429-670c-4997-ad14-e0d7305827c0","timestamp":"2026-06-14T05:05:13.626Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"218fd429-670c-4997-ad14-e0d7305827c0","isSidechain":false,"attachment":{"type":"command_permissions","allowedTools":["Bash","Read","Monitor"]},"type":"attachment","uuid":"ea76faa9-fd79-44b8-9998-2d4be14f4956","timestamp":"2026-06-14T05:05:13.626Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"ea76faa9-fd79-44b8-9998-2d4be14f4956","isSidechain":false,"attachment":{"type":"hook_additional_context","content":["CAVEMAN MODE ACTIVE (full). Drop articles/filler/pleasantries/hedging. Fragments OK. Code/commits/security: write normal."],"hookName":"UserPromptSubmit","toolUseID":"hook-34d39db2-886f-498c-8ef3-f2699a5eea1c","hookEvent":"UserPromptSubmit"},"type":"attachment","uuid":"531b5f95-22d0-4b06-95ac-950127fc98ad","timestamp":"2026-06-14T05:05:13.722Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"type":"last-prompt","lastPrompt":"/spt:live perinne","leafUuid":"531b5f95-22d0-4b06-95ac-950127fc98ad","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"mode","mode":"normal","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"permission-mode","permissionMode":"bypassPermissions","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"bridge-session","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","bridgeSessionId":"cse_01WxPcUV9jv9hcXAk8781fFp","lastSequenceNum":0}
{"type":"last-prompt","lastPrompt":"/spt:live perinne","leafUuid":"531b5f95-22d0-4b06-95ac-950127fc98ad","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"mode","mode":"normal","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"permission-mode","permissionMode":"bypassPermissions","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5"}
{"type":"bridge-session","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","bridgeSessionId":"cse_01WxPcUV9jv9hcXAk8781fFp","lastSequenceNum":0}
{"type":"file-history-snapshot","messageId":"e4fb4383-bab6-49f9-a388-ebb803fe92c4","snapshot":{"messageId":"e4fb4383-bab6-49f9-a388-ebb803fe92c4","trackedFileBackups":{},"timestamp":"2026-06-14T05:05:26.258Z"},"isSnapshotUpdate":false}
{"parentUuid":"5ceb0b63-5ff3-4d24-a60f-d4e0fd3d9ce5","isSidechain":false,"promptId":"9a01e377-226e-4c91-84cf-aab728730d3b","type":"user","message":{"role":"user","content":"<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"},"isMeta":true,"uuid":"218cc222-8c8c-4ace-b6a1-bee69270e9d4","timestamp":"2026-06-14T05:05:26.241Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"218cc222-8c8c-4ace-b6a1-bee69270e9d4","isSidechain":false,"promptId":"9a01e377-226e-4c91-84cf-aab728730d3b","type":"user","message":{"role":"user","content":"<command-name>/exit</command-name>\n            <command-message>exit</command-message>\n            <command-args></command-args>"},"uuid":"e4fb4383-bab6-49f9-a388-ebb803fe92c4","timestamp":"2026-06-14T05:05:26.240Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}
{"parentUuid":"e4fb4383-bab6-49f9-a388-ebb803fe92c4","isSidechain":false,"promptId":"9a01e377-226e-4c91-84cf-aab728730d3b","type":"user","message":{"role":"user","content":"<local-command-stdout>See ya!</local-command-stdout>"},"uuid":"347b737f-1cf1-4b01-8dbb-72943f99e221","timestamp":"2026-06-14T05:05:26.240Z","userType":"external","entrypoint":"cli","cwd":"C:\\Users\\decid\\Documents\\projects","sessionId":"bbab0bcf-d611-4e12-bb8e-74267e2145c5","version":"2.1.173","gitBranch":"HEAD"}