Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mh4gf/claude-code/collect-permissionsnpx skills add MH4GF/claude-code --skill collect-permissionsgit clone --depth 1 https://github.com/MH4GF/claude-codeWrote 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/mh4gf/claude-code/collect-permissions)<a href="https://agentmods.dev/skills/mh4gf/claude-code/collect-permissions"><img src="https://agentmods.dev/badge/skills/mh4gf/claude-code/collect-permissions.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 | $0.00046 | $0.00727 |
| Opus 5 | $0.00023 | $0.00364 |
| Sonnet 5 | $0.00009 | $0.00145 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade B, and why
collect-permissions scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
allowed-tools: Bash(bash *collect_permissions.sh*), Read(~/.claude/settings.json) What it actually says
候補抽出と分類のみを行う noninteractive スキル。~/.claude/settings.json への実追加は /tq:create-action で別 action にディスパッチし、人間の承認下で実行する。
手順
1. 候補抽出
bash ~/.claude/skills/collect-permissions/scripts/collect_permissions.sh
スクリプト出力はフィルタ適用済みの候補リスト。
2. 分類
各候補を以下の順で判定:
- auto memory の除外ルール (
feedback_collect_permissions.md) に該当 → 除外 - <review_guidelines> に該当 → 除外
- 残りは「追加候補」
<review_guidelines>
gog: query 系（gog auth status等）は許可、操作系（gog gmail thread modify等）は除外- プロジェクト固有 Skill: グローバル追加すべきか判定（基本除外、明らかに汎用な場合のみ追加）
- 引数境界が曖昧で過去収集で「保留」が繰り返される候補（例:
cc-open *）: 除外し auto memory に追記 </review_guidelines>
3. 分岐
追加候補 0 件 — そのまま終了。/tq:done で outcome: 追加候補なし を記録するだけ。/tq:create-action は呼ばない。
追加候補 1 件以上 — /tq:create-action で settings.json 追加 action をディスパッチ。複数候補は 1 つの action にまとめる。
instruction の形式は次のとおり。見出しに **bold** を使い、## 形式の markdown headers は避ける。## を入れると Bash built-in safety Newline followed by # inside a quoted argument で deny される。
claude-code リポジトリの user-scope/settings.json (= ~/.claude/settings.json の symlink 先) の permissions.allow に以下を追加してください。アルファベット順を維持し、追加後 /commit で claude-code リポジトリにコミット:
- "<entry1>" — <理由>
- "<entry2>" — <理由>
4. auto memory 更新
feedback_collect_permissions.md への追記基準は以下
- 既存除外ルールでカバーできない新カテゴリを判断したとき
<review_guidelines>の「引数境界が曖昧」枠で新たに除外候補を発見したとき
該当しなければ更新しない。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 55 lines · 46 tokens per session scan B 96ca44d4d66f
collect-permissions is a skill published in the GitHub repository MH4GF/claude-code (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 727 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…