Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/s977043/plangate/skill-policy-router)<a href="https://agentmods.dev/skills/s977043/plangate/skill-policy-router"><img src="https://agentmods.dev/badge/skills/s977043/plangate/skill-policy-router/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/s977043/plangate/skill-policy-router"><img src="https://agentmods.dev/badge/skills/s977043/plangate/skill-policy-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.02580 |
| Opus 5 | $0.00046 | $0.01290 |
| Sonnet 5 | $0.00019 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
skill-policy-router scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Policy Router
正本(sync 元):
.agents/skills/skill-policy-router/SKILL.md。scripts/sync-plugin-plangate.shが.agents/skills/を読み取りplugin/plangate/skills/を機械生成する。.claude/skills/と.codex/skills/は sync 対象外の配布先のため、正本更新時に同一内容を手動で追従させる。
Intent と Mode を入力として受け取り、必要な Skill とゲート要件(GatePolicy)を structured JSON で返す。
参照解決順(.claude/rules/*.md / 導入先で必ずこの順に探す)
本 Skill は Mode / lite_eligible の定義正本として .claude/rules/mode-classification.md を
参照する(§Iron Law / §lite_eligible の扱い)。このパスは上流リポジトリ基準のため、導入先では
次の順で探索する:
- 導入先リポジトリの
.claude/rules/mode-classification.md - 無ければ plugin root 配下
<plugin_root>/rules/mode-classification.md。<plugin_root>は Bash でls "${CLAUDE_PLUGIN_ROOT}/rules/"を実行して展開・確認した 絶対パス(Read ツールは絶対パスを要求し環境変数を展開しないため、${CLAUDE_PLUGIN_ROOT}/...という文字列をそのまま Read しない)。変数が空・未設定ならキャッシュを glob で推測せず 3 へ進む - どちらにも無い場合は 「正本
mode-classification.mdを参照できなかった」と明示し、 推測で内容を補わない
Iron Law
GATE POLICY IS DETERMINED BY MODE, NOT BY INTENT
GatePolicy の必須 / 任意判定は Mode によって決まる。 Intent はスキルの優先度や追加推奨にのみ影響する。
Mode の定義・判定基準(変更ファイル数・リスク・
lite_eligible)は.claude/rules/mode-classification.mdが単一正本。本スキルは確定済み Mode を入力として受け取り GatePolicy へ写像するのみで、Mode 自体は判定しない。下の「Mode 別ポリシー表」は Mode→GatePolicy の写像であり Mode の定義ではない(重複定義ではない)。
Common Rationalizations
| こう思ったら | 現実 |
|---|---|
| 「小さな feature だから approval 不要」 | Mode が high-risk ならば Intent に関わらず approval は必須 |
| 「docs なら worktree は不要では?」 | Mode が high-risk なら docs でも worktree が必要 |
| 「ultra-light なら全部スキップでいい」 | verify は ultra-light でも必須 |
GatePolicy 型定義
{
"requiredSkills": ["<skill-name>", "..."],
"optionalSkills": ["<skill-name>", "..."],
"requiresUserApproval": "<boolean>",
"requiresEvidence": "<boolean>",
"requiresFailingTestFirst": "<boolean>",
"requiresWorktree": "<boolean>"
}
Skill 識別子:
| 識別子 | 対応 Skill / 行動 |
|---|---|
think |
設計・計画の立案(plan.md 生成) |
hunt |
コードベース調査(Grep / Glob 探索) |
check |
セルフレビュー(diff-audit Skill、旧 self-review) |
tdd |
テスト駆動開発(failing test first) |
verify |
受け入れ検査(test-cases.md 突合) |
worktree |
独立ブランチでの作業(worktree 分離) |
review |
外部レビュー(human / external AI) |
approval |
人間の明示的承認取得 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 214 lines · 93 tokens per session scan A 4356b4dce51f
skill-policy-router is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 2,580 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-maintenance
Automated skill maintenance tool (v6 — Unified Registry + Snapshots). Full scan: [Orphan] migrate misplaced skills from category dirs OR standalone skills/<name>/ to auto-generated/, [Sync] auto-generated/ vs registry lifecycle diff (new/deleted/revived + description auto-sync via lifecycle field), [Reg]…
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.