菜单
Print every policy enforcement point declared in plugins/diagnostics/registry/policies.json — id, verdict, plugin, hook event, severity, bypass — grouped by verdict. Single discoverable index of what the harness blocks, anchors, nudges, or logs at runtime.
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
Use when the user describes a multi-step feature or refactor and you need to decide whether to handle it solo, dispatch a parallel `/fan-out`, or run a `/worktree-team` planner→generator→reviewer pipeline. Outputs a routing recommendation with the reasoning behind it.
Use whenever the user asks to apply the same operation to many independent files or components — bulk migration, batch refactor across controllers, parallel exploration of unrelated subsystems. Dispatches one subagent per file with a shared prompt template, then collects the results.
Use to toggle the safe-mode flag at .claude/safe-mode. The flag is written automatically by consecutive-failure-guard once tool failures hit FORGE_SAFE_MODE_THRESHOLD (default 5), and block-destructive.sh denies every Bash/Write/Edit while it exists. /safe-mode off clears the flag, logs the exit, and prompts /postmortem; /safe-mode on enters manually; /safe-mode status reports current state.
Run the 5-stage Token Transformation Pipeline (TRAE §5.2.2) over the current session state — Collection, Ranking, Compression, Budgeting, Assembly. Emits a concrete next-action recommendation (/compact, /lean-md, or /progress-log + fresh session) instead of a generic warning.
Audit or scaffold a CLAUDE.md against the Karpathy 4-section structure (Think Before Coding · Simplicity First · Surgical Changes · Goal-Driven Execution). Companion to /lean-md — structure audit, not size trim.
Audit the project against the R.E.S.T. framework (TRAE) — Reliability, Efficiency, Security, Traceability. Reads ledger entries, hook state, and artifact presence across long-session + policy-gateway + context-engine + traces. Single PASS/WARN/FAIL table. Cross-cut meta-surface.
| name | policies-list |
| description | Print every policy enforcement point declared in plugins/diagnostics/registry/policies.json — id, verdict, plugin, hook event, severity, bypass — grouped by verdict. Single discoverable index of what the harness blocks, anchors, nudges, or logs at runtime. |
| when_to_use | Reach for this when onboarding to forge-studio, before turning a plugin off and wanting to know what enforcement disappears with it, or while writing docs that need to cite a policy by id (FS01–FS42). Do NOT use to *change* a policy — the registry indexes existing scripts; edits go in the source script and `rules.d/` patterns, not here. Do NOT use for behavioral compliance audits — use `/rules-audit` instead; policies-list only inventories enforcement points. |
| disable-model-invocation | true |
| allowed-tools | ["Read","Bash"] |
| logical | report shows every registry entry grouped by verdict (deny/gate/anchor/nudge/log) with its FS-id, plugin, hook event, and bypass mechanism |
Read plugins/diagnostics/registry/policies.json and print one row per enforcement point. The registry is the single discoverable index of what the harness blocks, anchors, nudges, or logs at runtime.
| Verdict | Mechanism | Effect |
|---|---|---|
deny | PreToolUse hook returns exit 2 / {"decision":"block"} | Tool call refused |
gate | PreToolUse hook returns deny only when conditional check fires | Tool call sometimes refused |
anchor | UserPromptSubmit / SessionStart hook injects system-prompt text | Behavioral steer, no enforcement |
nudge | PostToolUse hook injects an advisory message | Soft suggestion, ignorable |
log | PostToolUse hook appends to ledger / counter | Telemetry feeds other policies |
bash plugins/diagnostics/skills/policies-list/scripts/render.sh
## Policy Enforcement Index
**Source:** plugins/diagnostics/registry/policies.json
**Entries:** {N}
### deny
| FS-id | Plugin | Hook | Bypass | Description |
|---|---|---|---|---|
| ... | ... | ... | ... | ... |
### gate
...
### anchor
...
### nudge
...
### log
...
/entropy-scan Check 13 catches registry rows whose implementation path no longer exists, and enforcement scripts on disk that have no registry entry. Fix in the registry, not by deleting evidence.