Borrowing it
Nothing to install: this file belongs to akiojin/unity-mcp-server. 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/akiojin/unity-mcp-server/main/.claude/commands/suggest-claude-md.mdgit clone --depth 1 https://github.com/akiojin/unity-mcp-serverWrote 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/commands/akiojin/unity-mcp-server/suggest-claude-md)<a href="https://agentmods.dev/commands/akiojin/unity-mcp-server/suggest-claude-md"><img src="https://agentmods.dev/badge/commands/akiojin/unity-mcp-server/suggest-claude-md.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00598 |
| Opus 5 | $0.00010 | $0.00299 |
| Sonnet 5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
suggest-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 8d 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.
What it actually says
CLAUDE.md改善提案コマンド
このコマンドは、現在の会話履歴を分析し、CLAUDE.mdに追記すべきルールや知識を自動的に提案します。
概要
AppBrewのたっくん氏が開発した手法に基づき、以下の3つの観点から会話を分析します：
- プロジェクト独自のルール: 標準的な実装ではなく、このプロジェクト特有の方法や制約
- 繰り返し指摘される内容: 同じ指摘が複数回出現し、ルール化が必要なパターン
- 複数箇所で統一すべき実装: 関連箇所で実装を揃えるべきパターン
使い方
-
コマンド実行
/suggest-claude-md -
提案内容の確認
- AIが会話履歴を分析し、CLAUDE.mdへの追記候補を提示します
- 各提案には、なぜそのルールが必要かの理由も含まれます
-
CLAUDE.mdへの適用
- 提案内容を確認後、以下のように指示してください：
この提案をCLAUDE.mdに追記してください - または、手動で必要な部分のみをCLAUDE.mdに追記することも可能です
- 提案内容を確認後、以下のように指示してください：
自動実行
セッション終了時（SessionEnd）またはコンテキスト圧縮前（PreCompact）に自動的にこのコマンドが実行されます。
自動実行を一時的に無効化したい場合は、環境変数を設定してください：
export SUGGEST_CLAUDE_MD_RUNNING=1
スクリプト実行
以下のスクリプトが会話履歴を分析します：
scripts/suggest-claude-md.sh
参考記事
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.
- 8d ago First seen · 57 lines · 20 tokens per session scan A d999b96a0d4e
suggest-claude-md is a command published in the GitHub repository akiojin/unity-mcp-server (34 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 598 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
init-workspace-flow-documentation
Phase 7 Documentation of init-workspace-flow.
harness-refresh
Refresh a target repository's existing harness by reviewing whether its agent-facing rules, knowledge store, and drift checks are still accurate.
ai-context
AI context file management has moved to ContextDocs: $ARGUMENTS.
context-guard
Context Guard hooks have moved to ContextDocs: $ARGUMENTS.
session-summary
Genera un resumen de lo que se hizo en esta sesión.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.