Borrowing it
Nothing to install: this file belongs to elchika-inc/ts-review-graph. 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/elchika-inc/ts-review-graph/main/CLAUDE.mdgit clone --depth 1 https://github.com/elchika-inc/ts-review-graphWrote 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/elchika-inc/ts-review-graph/claude-md)<a href="https://agentmods.dev/instructions/elchika-inc/ts-review-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/elchika-inc/ts-review-graph/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/elchika-inc/ts-review-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/elchika-inc/ts-review-graph/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 | $0.01927 | $0.01927 |
| Opus 5 | $0.00963 | $0.00963 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
ts-review-graph 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 9d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ts-review-graph
Commands
pnpm build # 全パッケージをビルド (tsc)
pnpm test # 全パッケージのテストを実行 (vitest)
pnpm lint # 全パッケージの型チェック (tsc --noEmit)
pnpm sync-version # cli/package.json の version を全配布物へ同期
# 特定パッケージのみ
cd packages/core && pnpm build
cd packages/mcp-server && pnpm build
cd cli && pnpm build
Architecture
pnpm monorepo。4 パッケージで構成:
| Package | Name | Role |
|---|---|---|
packages/core |
@elchika-inc/ts-review-graph-core |
グラフ構築・クエリエンジン (SQLite + ts-morph) |
packages/mcp-server |
@elchika-inc/ts-review-graph-mcp-server |
MCP サーバー (8 ツール) |
packages/plugin |
(配布専用) | Claude Code プラグイン (commands/hooks/skills) |
cli/ |
@elchika-inc/ts-review-graph |
CLI ツール |
依存関係: mcp-server → core、cli → core。plugin は Node package/build を持たず、Markdown・hooks.json・shell hook scripts で構成する。
Key Files
packages/core/src/db.ts— SQLite スキーマ定義とopenDbpackages/core/src/analyzer.ts— ts-morph による AST 解析packages/core/src/blast.ts— BFS ブラスト半径計算 (SQL Recursive CTE)packages/core/src/updater.ts— 増分更新ロジックpackages/mcp-server/src/tools/index.ts— 全 MCP ツール定義と登録cli/src/index.ts— CLI エントリポイント (install/build/update/status/uninstall)cli/src/codex-config.ts— Codex 用.codex/config.tomlの追記。中止の粒度は2段(判定軸は「ファイルを正しく読めたか」)— 詳細はCodexConfigUpdateの doc コメント
Database Schema
SQLite 4 テーブル: nodes、edges、file_hashes、meta
Edge kinds: IMPORTS_FROM | TYPED_BY | IMPLEMENTS | EXTENDS | HAS_TEST
重要: nodes.file と nodes.id はプロジェクトルート相対の POSIX パスで保存する。
絶対パスで保存すると、リポジトリの移動・worktree・別マシンでのクローンでグラフが
無言で全件ミスする(実障害あり)。DB へ保存するすべてのファイルパスは共通
ユーティリティ toProjectRelative を通す。analyzer.ts ではルート外を除外する
toRelativeOrNull を経由する。
重要: edges.target_id に意図的に REFERENCES を付けていない。増分更新でファイルを
削除するとき、source_id が削除ファイルのエッジだけを CASCADE で消し、
逆方向 (B→A) エッジは残す必要があるため。
重要: meta テーブルはグラフの構築条件(schema_version / tsconfigs /
built_at / built_root)を記録する。checkGraphHealth() がこれを使って検疫する。
meta 不在の DB は旧形式として fail-closed で拒否される。
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.
- 9d ago First seen · 123 lines · 1,927 tokens per session scan A 04720a5672d0
ts-review-graph CLAUDE.md is an instructions file published in the GitHub repository elchika-inc/ts-review-graph (0 stars, last pushed 24d ago), licensed MIT. It adds 1,927 tokens to every session, about $0.0096 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 instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.