菜单
Read-only view of the vault. Prints the landed-vs-corrected matrix per agent and a breakdown of correction tags across all deliberations. Writes nothing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Govern AI spend without surveilling your team — the AI-spend governance loop. Set OKRs, harden the right context (tray→slate), bounded agents surface a finding ready for ratification, ratify a policy to the provenance trail, get a spend-ROI report that cites its sources. The leader governs usage; the team's private context is never read.
The parallel per-agent swarm that beats cold-start. After install, each bounded agent reads its canonical source (git/claude-code → Analyst, granola → SDR, cross-stream → Auditor) in parallel and posts a candidate — the one fact, commitment, or risk worth acting on — before any deliberation. Read-only, LLM-optional. Run this to show the vault won't start empty.
Twelve-agent deliberation on the user's psychological state across four registers (Structural / Somatic / Temporal / Symbolic). Asks three forced-choice questions, runs all 12 agents via Opus 4.7 in parallel, surfaces their disagreement grouped by register, and writes the user's correction — tagged from the canonical taxonomy — to the local vault.
The 60-second taste of Liminal. Runs one bounded deliberation on a sample brief — three agents read the same brief and disagree, at least one refuses out of its lane, you correct one read, and the correction becomes the record. Ends by pointing at the desktop app so the vault outlives the session. Run this first.
Audit an existing Claude Code workspace for canon-substrate gaps — the failure mode where users build sophisticated agent stacks without a CORPUS_MAP / SCHEMA / decisions/ layer underneath, leaving every agent's "consult on demand" reference list resolving to nothing. Reports ship-blocking issues, fragile-but-working issues, and noise. Use when invited into someone's `.claude/agents/` directory to do an audit-and-recommend pass.
Materialize the canon-substrate foundation pack into a target workspace. Reads a diagnose-substrate JSON report + a small config file, copies the recommended template files into the target, substitutes high-frequency placeholders (PROJECT NAME, OWNER NAME, sensitivity tiers), and emits a landing prompt the user pastes into their Claude Code session to finish the customization. Pairs with diagnose-substrate — diagnose first, scaffold second. Step (b) of SPEC §14's productized Diagnostic + Foundation Pack pattern.
| name | history |
| description | Read-only view of the vault. Prints the landed-vs-corrected matrix per agent and a breakdown of correction tags across all deliberations. Writes nothing. |
| disable-model-invocation | true |
| allowed-tools | Bash(node *) |
| argument-hint | [optional: --since-days=N] |
Read-only. The record is the moat. This skill reads it and shows the shape of disagreement over time.
Run the history script. If $ARGUMENTS contains --since-days=N, pass it along.
node ${CLAUDE_PLUGIN_ROOT}/skills/history/history.js
Or:
node ${CLAUDE_PLUGIN_ROOT}/skills/history/history.js --since-days=30
Returns JSON with:
deliberations — total count in windowcorrections — total correction count in windowlegacy_imported — count of legacy-import rows (pre-substrate v0.2)matrix — per agent: landed, corrected, by_tag (counts by canonical tag)note — the structural claim: the agents do not converge; the record doesShow the matrix as a table. Do not editorialize. Do not average. Do not suggest improvements. The user reads their own pattern.
If the user asks "what does this mean", state the claim once: the agents do not adapt. The record does. What they miss, and how you tag what they miss, is the data.