Borrowing it
Nothing to install: this file belongs to shuji-bonji/houki-egov-mcp. 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/shuji-bonji/houki-egov-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/shuji-bonji/houki-egov-mcpWrote 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/shuji-bonji/houki-egov-mcp/agents-md)<a href="https://agentmods.dev/instructions/shuji-bonji/houki-egov-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/houki-egov-mcp/agents-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/shuji-bonji/houki-egov-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/houki-egov-mcp/agents-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 | $0.02617 | $0.02617 |
| Opus 5.5 | $0.01047 | $0.01047 |
| Sonnet 5.5 | $0.00523 | $0.00523 |
| Haiku 4.5 | $0.00262 | $0.00262 |
Grade A, and why
houki-egov-mcp AGENTS.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 19d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
エージェント(Claude Code / Cowork のセッション)がこのリポジトリで作業するときの目次です。手順の本文はここには書きません。仕様とコードを 2 本の PR で変える運用の全体は、spec-ids の docs/operations.md にあります。
仕様の正本
- 意図の正本は
specs/current/です。Wiki・Discussions・README・ツールの description は正本にしません。 - 変更は
specs/changes/<yyyymmdd>-<slug>/に出し、人が承認するまで Coder を起動しません。 - 承認された差分は Spec Publisher が
specs/current/に取り込み、差分のフォルダーをspecs/releases/<実装を出したタグ>/<yyyymmdd>-<slug>/へ移します(git mv)。移すときに proposal.md の「状態」を取り込み済みにします。取り込みでは current の spec.md に承認を書き足しません(下の「承認の記録」)。 - Coder は
specs/current/の本文を書き換えません。実装から仕様へ戻したい発見は、新しいspecs/changes/に書きます。 - 受入テストの
itの名前には仕様 ID(例:SPEC-EGOV-GET-LAW-001)を含めます。npx spec-ids check(@shuji-bonji/spec-ids)が仕様とテストの ID を突き合わせ、CI(spec-gate)で走ります。
仕様 ID
- 形式は
SPEC-<領域>-<機能>-<3 桁>です(例:SPEC-EGOV-GET-LAW-001)。領域EGOVはこのリポジトリを表します。機能はspecs/current/<dir>/spec.mdのディレクトリ名を大文字にし、_を-にしたものです(get_law→GET-LAW)。番号は機能ごとに 001 からの通し番号です。 - ディレクトリ名は、MCP ツールならツール名そのもの(
get_law)です。ツールでない外から見える単位は、common_errors(全ツールに共通するエラー応答と引数の検査)、db_schema(ローカル DB)、cli_<コマンド>(cli_entry/cli_bulk_download/cli_sync/cli_status)に置きます。spec.md の front matter のkindにtool/common/db/cliのどれかを書きます。 - 機能ごとに数列を分けるので、並行するブランチが衝突するのは同じ機能の仕様を同時に足したときだけです。
spec-ids checkは、見出しの ID の機能がディレクトリ名と一致することも検査します。 - 一度使った番号はその機能の中で再利用しません。仕様を外すときは
specs/changes/のREMOVEDに書き、テストからも ID を外します。 - 新しい ID は
npx spec-ids next specs/current/<dir>/spec.md(またはディレクトリ名npx spec-ids next get_law)で取ります。その機能の見出しの最大番号 +1 です。複数なら--count 3。番号の予約はしないので、同じ番号が 2 つの見出しに現れたら、マージ時にspec-ids checkの重複検知で止まります。 - ID の形式(正規表現・機能の導き方・組み立て)は
@shuji-bonji/spec-idsが決めています。このリポジトリで決めるのはspecs/spec-ids.jsonの領域EGOV、接頭辞なし、テストの globsrc/**/*.test.tsだけです。
PR の種類
仕様とコードを、同じリポジトリの別の資産として扱います。人が振る舞いを承認するのは仕様 PR と初版起こしだけです。実装 PR で問うのは「承認済みの文と、テストと、コードが同じか」で、振る舞いに何を許すかの判断は実装レビューへ戻しません。CI の pr-scope(npx spec-ids pr-scope。@shuji-bonji/spec-ids 0.4.0 以降)が、ブランチ名の接頭辞ごとに変えてよいパスを検査します。
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.
- 19d ago Changed · +32 tokens per session 560e71495f80
- 20d ago Changed · +15 lines · +567 tokens per session 0232bc18193e
- 1mo ago First seen · 54 lines · 2,018 tokens per session scan A 8e8e157a04f7
houki-egov-mcp AGENTS.md is an instructions file published in the GitHub repository shuji-bonji/houki-egov-mcp (2 stars, last pushed 19d ago), licensed MIT. It adds 2,617 tokens to every session, about $0.0105 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 2026-09-28.
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.