Borrowing it
Nothing to install: this file belongs to s977043/PlanGate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/s977043/PlanGate/main/CLAUDE.mdgit clone --depth 1 https://github.com/s977043/PlanGateWrote 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/instructions/s977043/plangate/claude-md)<a href="https://agentmods.dev/instructions/s977043/plangate/claude-md"><img src="https://agentmods.dev/badge/instructions/s977043/plangate/claude-md/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/instructions/s977043/plangate/claude-md"><img src="https://agentmods.dev/badge/instructions/s977043/plangate/claude-md.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 | $0.03035 | $0.03035 |
| Opus 5.5 | $0.01214 | $0.01214 |
| Sonnet 5.5 | $0.00607 | $0.00607 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade A, and why
PlanGate CLAUDE.md 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 18d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
実行契約:
docs/ai/core-contract.md（Iron Law / Stop rules / Output discipline の正本） プロジェクトルール:docs/ai/project-rules.md（必読、AI 運用 4 原則の正本）
Claude Code 固有参照
- エージェント / コマンド / スキル:
.claude/agents//.claude/commands//.claude/skills/ - 運用ルール:
.claude/rules/（hybrid-architecture 等は常時。orchestrator-mode は親 PBI 分解時のみ参照） - 共有スキル:
.agents/skills/（Codex CLI と共用） - ワークフロー詳細:
docs/ai-driven-development.md/ Orchestrator:docs/orchestrator-mode.md - サブエージェント委譲プロトコル:
docs/ai/subagent-delegation/README.md（派遣プロンプト必須8要素 / OUTCOME契約 / 行動規範 / PlanGateフロー接続。既存の C-3/C-4 ゲートおよび orchestrator-mode の Gate 不変条件は変更しない）
v8.24.0 計画レビューの対話フィードバックと Ratchet の実差分判定（最新リリース機能）
最新リリース: v8.24.0（2026-10-12）v8.23.0 タグ以降に main へ蓄積した 36 コミット・PR 36 件を反映（
1f091e97時点の測定値。実測:git rev-list --count v8.23.0..1f091e97。PR 36 件のうち #1504 は v8.23.0 の release note 保存）。主題は 計画レビューの回答を機械可読に受け取る経路（opt-in）・ai-loop V2 の Ratchet を repository の実差分で判定すること・導入先 repo でのbin/plangateの使い方（#1497）に Skill / Agent / Command の案内を合わせること。主要変更:plangate renderの対話フィードバック HTML（#1527。任意のreview-questions.jsonから生成し、回答・保留・未回答を plan / questions の SHA-256 つきで JSON にエクスポートする。フィードバック専用で承認ではない・質問を渡さない従来の出力は byte 同一）・エクスポート JSON の fail-closed 検証器scripts/validate_plan_feedback.py（#1534。鮮度の確認であり承認・gate には影響しない）・実 Chromium での検証（#1536 / #1542 / #1551。CI に 2 job を追加）・Ratchet の delta を deterministic scope observer へ（#1516。新規scope_observer.py）・Ratchet の expected prevention claim の束縛（#1495。claim は prevention evidence ではない）・外部 verifier P1 を P0 preflight の背後へ（#1511）・plugin の案内文 13 ファイル（#1512 / #1518 / #1538 / #1539 / #1561 / #1563。project root の解決順・retained memory の読み込み境界・workflow-conductorの見出し重複の解消。文面のみで挙動は不変。/plugin updateには version bump が要る）・C-3 ゲートの記述に外部レビュー Decision → c3_status の対応を追加（#1563 / #543。未知値・欠落は人間 C-3 強制。bin/plangateの承認判定は不変。ta-77 の承認面台帳を同時に更新）・適用待ち apply スクリプトの棚卸し（#1563 で 2 本適用・#1565 で 2 本削除。残る 3 本と検出器の偽陰性は既知の課題 #1562）・pre-push.sampleのマージ済みブランチ名の再作成ガード（#1552。push 先 ref で判定する opt-in のローカル hook）・CI の Test job で ta-61 を並列度 2 に（#1555。kill-switch はPG_T61_PARALLEL=1・merge 後 5 run の観測は閾値内）・運用方針の文書化（#1549 実践進化 / #1548 Issue 棚卸し playbook / #1547 PR テンプレートの Rollback / Detection 節）。bin/plangateとschemas/は変更ゼロ。破壊的変更を宣言した commit は 0 件。semver は minor（Human 決定 2026-10-11）。PlanGate 本番フロー WF-00〜07 は不変・NO MERGE BY AI／C-4・merge は Human-owned 固定。リリース履歴の正本はCHANGELOG.md。
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.
- 18d ago Changed · -73 tokens per session 027a6b711ea4
- 23d ago Changed · -131 tokens per session 7d6b536e69bd
- 28d ago Changed · +142 tokens per session 96bd4b612069
- 1mo ago Changed · +236 tokens per session ccf7ef122d42
- 1mo ago Changed · +20 lines · +464 tokens per session a90193bc6513
- 1mo ago First seen · 47 lines · 2,397 tokens per session scan A 9755d4ef78eb
PlanGate CLAUDE.md is an instructions file published in the GitHub repository s977043/PlanGate (2 stars, last pushed today), licensed MIT. It adds 3,035 tokens to every session, about $0.0121 per session on Opus 5.5. 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 2026-09-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.