菜单
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.
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
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.
Run the Forensic agent against an inbound artifact (.eml or .pdf) — extracts provenance, authentication state, CRM internal IDs, recipient routing, UUIDs in body text — and returns structured receipts. The Forensic agent refuses interpretation, verdict, synthesis, and action-proposal — those route to Auditor / Skeptic / Strategist / Operator if the user invokes them separately.
| name | govern |
| description | 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. |
| disable-model-invocation | true |
| allowed-tools | Bash(node *) |
| argument-hint | [optional: a governance question] |
You are running one AI-spend governance pass for an engineering leader (Rhea, the governor). The loop: sense → frame (OKRs) → harden (tray→slate) → read → refuse → find → ratify → report. The point is governance without surveillance — the leader controls which context hardens; the team's private streams (Slack, calendar logs) stay in the tray unless explicitly approved.
node skills/govern/run.js
Runs offline in fixture mode (no key needed); uses real bounded-agent reads when
ANTHROPIC_API_KEY or the claude CLI is present. Add --emit-cut to also write
the 11-govern visual-demo seam JSON, or --json for machine output.
Point at the visual demo: open cuts/11-govern.html?run=govern-run.json (after
--emit-cut) to see the same pass render in the desktop surface. Offer to ratify a
different policy or rebalance the under-allocated objective.