KeiSeiKit-1.0/skills/sleep-on-it/SKILL.md
Parfii-bot 3759fb0f64 fix(audit-batch): CI green + RULE 0.4/0.16/0.18 honesty pass
12-agent audit (2 waves Opus+Sonnet, 6 slices each) flagged 3 HIGH-tier
issues that BOTH waves agreed on, plus 5 doc-honesty findings. This
batch fixes the lot.

== CI green (was failing on main 94a7d68) ==

- _primitives/_rust/Cargo.toml — workspace tokio gains `io-std` feature
  (needed by kei-mcp/src/main.rs which calls tokio::io::{stdin,stdout})
- _primitives/_rust/kei-mcp/Cargo.toml — dev-deps tokio gains `test-util`
  feature (needed by tests/tools_call_timeout.rs for tokio::time::advance
  and Builder::start_paused). Both verified locally:
  `cargo check -p kei-mcp` ✓
  `cargo test --no-run -p kei-mcp` ✓ (3 test binaries link)
  [REAL: ran 2026-05-03 in this session]

== HIGH-tier audit fixes (consensus across waves) ==

1. SQLi escape in agent-outcome-backfill.sh:110
   - 4 of 12 agents flagged: TOOL_USE_ID was JSON-derived and
     interpolated raw into SQL. Allowlist on $SHIPPED protected today
     but a future case-statement removal opened the surface.
   - Fix: tiny `_sql_esc` helper that doubles single-quotes (SQL-99
     standard escape), applied to SHIPPED + TOOL_USE_ID. STUBS already
     integer-validated.

2. PRAGMA user_version=9 in install/sql/outcome-only-schema.sql
   - W1 outcome-only critic flagged: the SQL fallback installed a
     v9-equivalent flat schema but left user_version=0. A LATER
     `kei-ledger init` (e.g. when user upgrades to full kit) would
     re-run migrations v1-v9 and ALTER TABLE ADD COLUMN duplicate-error
     mid-migration → broken DB.
   - Fix: set PRAGMA user_version=9 before COMMIT so the binary's
     migration runner sees current ≥ target and short-circuits.

3. backup_file mv→cp + uninstall macOS-portable awk
   - W1+W2 outcome-only flagged: lib-backup.sh uses `mv` which DELETES
     the target before _jq_merge_hooks runs; `|| true` swallowed the
     subsequent jq read-error → silent settings.json loss.
   - Fix in lib-profile-outcome-only.sh: `cp -p` aside, drop `|| true`,
     return 1 on merge failure (trap restores).
   - PROFILE-OUTCOME-ONLY.md uninstall used GNU sed `,+1` extension
     which BSD sed (macOS) does not support — uninstall silently
     no-op'd on macOS, leaving orphan CLAUDE.md text.
   - Fix: replace with portable `awk` recipe; also added `rm -f` for
     the agent-toolstats.jsonl sidecar (privacy completeness).

== Doc honesty pass (RULE 0.18 numerics + RULE 0.4 citations) ==

4. README.md count drift — verified all values against filesystem:
   * 102→105 Rust crates (Cargo.toml workspace `members` count)
   * 67→68 skills (`ls skills/ | wc -l`)
   * 35→38 hooks (`grep -c '"command":' settings-snippet.json`)
   * 37→38 agent manifests (`ls _manifests/*.toml | wc -l`)
   * 82→85 substrate blocks (`find _blocks/ -name '*.md' | wc -l`)
   * 18 capability atoms VERIFIED via `find _capabilities/ -name '*.md'`
     (encyclopedia §3 row count of 17 is in a separate file and is a
     known internal display issue, not changed in this commit)
   * 495→565 active DNAs (per docs/DNA-INDEX.md header 2026-05-03)
   Each value now carries a `[REAL: <command>]` style trailer per
   RULE 0.18.

5. README.md DNA "80-char identity" → "≥33-char variable-length"
   - W1+W2 reviewer-pass flagged FALSE: docs/DNA-FORMAT.md SSoT says
     minimum 33 chars; 80 was nowhere in code or spec
   - Fix in README.md:36 + docs/PHILOSOPHY.md:39 + docs/DNA-INDEX.md:1352

6. README.md "Eleven install profiles (... Cursor / Continue / Zed /
   Aider / Docker / Nix)" — Cursor/Continue/Zed/Aider/Docker/Nix were
   never install profiles, they were bridge targets
   - Fix: list 12 actual profiles from _primitives/MANIFEST.toml,
     mention bridges as separate concept

7. .claude-plugin/plugin.json license MIT → Apache-2.0
   - W2-Sonnet reviewer flagged: LICENSE file is Apache-2.0 (since
     2026-04-30 per NOTICE), but plugin.json still declared MIT —
     plugin marketplace would show wrong license

8. docs/ARCHITECTURE.md:318 placeholder URL `https://example.invalid/...`
   - W2-Sonnet reviewer flagged: dead link in published docs
   - Fix: remove the bad href, describe ssl-rule-file as per-user
     install outside the public repo

9. skills/sleep-on-it/SKILL.md Wagner et al. 2004 citation
   - W1+W2 reviewer flagged RULE 0.4 violation: citation without
     verification marker
   - Fix: added [VERIFIED: doi:10.1038/nature02223] + clarification
     that the original paper showed slow-wave-sleep (not strictly REM)
     insight gain — our metaphor is a loose mapping

10. encyclopedia/substrate-overview.md §5 fabricated TS deps
    - W1-Opus doc-consistency flagged RULE 0.4.b violation: 5 of 6
      package rows had INVENTED dependency strings
      (`recall-ai-sdk ^1.0.0`, `nodemailer-mock ^2.0.0`,
       `telegram-typings ^4.10.0`, etc — none exist in the actual
      package.json files)
    - Fix: regenerated table from real `package.json` reads via
      `node -p "require(...).dependencies"` for each of the 6 packages
    - Fix: also corrected version drift (5 packages all 0.14.0 now)

Verification:
- Outcome-only end-to-end install against fake $HOME succeeds:
  hooks installed, ledger schema at user_version=9, settings.json
  created cleanly, all 5 documented files present
  [REAL: ran 2026-05-03 in this session]
- `cargo check -p kei-mcp` + `cargo test --no-run -p kei-mcp` clean

Audit findings NOT yet addressed (deferred to next batch):
- README:65 git clone github URL — repo is private; reviewer flagged
  external strangers cannot clone; will resolve via Quick Start rewrite
- npm.pkg.github.com / @keisei84 leftover sweep — both waves verified
  ZERO refs, no fix needed
- safeEqual timing leak in TS server (W2 sec MEDIUM)
- HTTP server bind 0.0.0.0 (W2 sec MEDIUM)
- Unbounded request body (W2 ci MEDIUM)
- --dry-run silent ignored on non-outcome profiles (W1+W2 MEDIUM)
- Doc-link missing for MEMORY/DNA/LEDGER format specs from README

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-03 19:09:59 +08:00

5.2 KiB
Raw Blame History

name description argument-hint
sleep-on-it Defer a hard question, research task, or design comparison to the nightly remote agent (KeiSeiKit v0.12.0 incubation layer). Runs on top of the v0.11 sleep-sync pipeline — user fills one free-text field plus three clicks, task lands in sync-repo/sleep-queue/ and is processed before REM consolidation. Up to 5 tasks per night, 15 minutes each. Pure-click wizard except the single task-description field. (no arguments)

Sleep On It — Incubation Wizard (index)

When to use

  • Deferring a hard question, research task, or design comparison to the nightly cloud agent for overnight processing.
  • Queuing up to 5 tasks per night (15 min each) to be processed before the REM consolidation pass.
  • Requires v0.11 sleep-sync already configured; use /sleep-setup first if not.

Biological analog: the "sleep on it" insight effect documented by Wagner et al. 2004, Nature 427:352355 [VERIFIED: doi:10.1038/nature02223] (the original paper showed insight gain after a sleep period that included slow-wave sleep, not strictly REM; our metaphor is a loose mapping). During the day the user submits open questions, research tasks, or design comparisons via this wizard; the nightly cloud agent processes the queue before its existing REM consolidation pass and writes results to sync-repo/sleep-results/.

This SKILL.md is the INDEX. Each phase lives in its own file and is executed in order. Never skip a phase. Never re-order phases.


Prerequisites (hard fail fast if missing)

  • v0.11 sleep-sync must be configured (~/.claude/secrets/.env contains KEI_MEMORY_REPO_PATH, KEI_MEMORY_SSH_KEY, and the sync-repo exists under that path with a .git/ subdir).
  • _primitives/kei-sleep-queue.sh exists at ~/.claude/agents/_primitives/kei-sleep-queue.sh and is executable.

If either is missing, print the single line

v0.11 sleep-sync not configured — run `/sleep-setup` first, then retry.

and exit the wizard. Do not attempt to queue anything offline.


Pipeline overview (6 phases, 5+ AskUserQuestion)

Phase File Purpose AskUserQuestion
1 phase-1-intake.md One free-text field: the question / task 0 (prompt, non-empty validate)
2 phase-2-type.md Task type: deep / pipeline / pattern / compare / custom 1 (click)
3 phase-3-priority.md Priority: tonight / FIFO / weekly 1 (click)
4 phase-4-format.md Output format: markdown / ADR / checklist / table 1 (click)
5 phase-5-submit.md Preview frontmatter + body, submit / edit / abort 1 (click)
6 phase-6-ack.md Acknowledgment with UUID + queue path + run ETA 1 (click)

Minimum AskUserQuestion count: 5. All clicks except the single free-text task description in Phase 1.


Variables the pipeline produces

Name Set in Meaning
TASK_TEXT Phase 1 Free-text task description (non-empty)
TASK_TYPE Phase 2 deep / pipeline / pattern / compare / custom
PRIORITY Phase 3 night / fifo / weekly
FORMAT Phase 4 md / adr / checklist / table
SUBMIT_ACTION Phase 5 submit / edit / abort
QUEUE_PATH Phase 5 Path of the queue file written by kei-sleep-queue.sh add
UUID Phase 5 UUID assigned by the helper

Final report (emit after Phase 6)

=== SLEEP-ON-IT REPORT ===
UUID:           <UUID>
Queue file:     <QUEUE_PATH>
Task type:      <TASK_TYPE>
Priority:       <PRIORITY>
Output format:  <FORMAT>
Next run ETA:   <UTC cron time from .keisei-sync.toml>
Results land:   sync-repo/sleep-results/<UUID>.md

Rules (apply throughout — enforced at every phase)

  • Pure-click contract. Only Phase 1 asks for free text; every other decision is an AskUserQuestion. No freeText outside Phase 1.
  • Idempotent. Re-running the wizard while a previous task is still pending is fine — each submission gets its own UUID and its own queue file. No "one pending at a time" constraint.
  • NO DOWNGRADE (RULE -1). If the helper rejects (invalid flag, sync push fails), surface 2-3 constructive fix paths — never "cannot submit".
  • NO HALLUCINATION (RULE 0.4). Never fabricate a UUID, queue path, or ETA — always echo the real helper output.
  • RULE 0.8 secrets. Queue files never embed tokens; env refs live in ~/.claude/secrets/.env only.
  • Silent failure (RULE 0.15). If the post-submit sync push fails, the queue file still lives locally and will be pushed on the next session-end dump. The wizard must NOT block on push failure.
  • Constructor Pattern (RULE ZERO). Every phase file < 100 LOC.

References

  • ~/.claude/rules/sleep-layer.md — RULE 0.15 full text (Phase A added v0.12.0)
  • _primitives/kei-sleep-queue.sh — the queue CRUD helper
  • _primitives/kei-sleep-sync.sh — the session-end-dump callback (also invoked by kei-sleep-queue.sh add after write)
  • _primitives/templates/sleep-incubation-prompt.md — cloud agent Phase A
  • _primitives/templates/sleep-trigger-prompt.md — cloud agent Phase B
  • skills/sleep-setup/ — v0.11 one-time sync-repo wizard (prerequisite)