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 skills add myths-labs/muse --skill git-security-guardgit clone --depth 1 https://github.com/myths-labs/museWrote 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/myths-labs/muse/git-security-guard)<a href="https://agentmods.dev/skills/myths-labs/muse/git-security-guard"><img src="https://agentmods.dev/badge/skills/myths-labs/muse/git-security-guard.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 | $0.00082 | $0.01388 |
| Opus 5 | $0.00041 | $0.00694 |
| Sonnet 5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
git-security-guard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Security Guard — 敏感信息泄露防护
触发时机
- 每次 git commit 前（自动）
- 每次 git push 前（自动）
- 新项目/新 repo 初始化时
- 用户要求安全检查时
Pre-Commit 检查清单
Step 1: 检查暂存文件名
git diff --cached --name-only | grep -iE '\.env|\.pem|\.p12|\.jks|\.key$|\.muse/|\.agent/|\.gemini/|memory/|convo/'
任何匹配 → 立即阻止 commit，报告给用户。
Step 2: 检查暂存内容中的 Key 模式
git diff --cached | grep -iE 'sk-[a-zA-Z0-9]{20}|AIzaSy[a-zA-Z0-9_-]{33}|gsk_[a-zA-Z0-9]{20}|sk_live_|sk_test_[a-zA-Z0-9]{20}|pk_live_|pk_test_[a-zA-Z0-9]{20}|eyJhbGci[a-zA-Z0-9_-]{50}|-----BEGIN.*(PRIVATE|RSA)|AKIA[0-9A-Z]{16}|ghp_[a-zA-Z0-9]{36}|whsec_|xoxb-|xoxp-|service_role'
任何匹配 → 立即阻止 commit，报告给用户。
Step 3: 排除误报
以下不算泄露：
.env.example中的占位符（your-api-key、sk_test_your-...）process.env.XXX引用（代码读环境变量，不是硬编码）node_modules/中的加密库代码- 公开合约地址（USDC/USDT 等已知合约）
- 文档中的"不要这样做"示例
禁止提交的文件模式
| 文件模式 | 原因 |
|---|---|
.env.local / .env.prod* / .env.vercel* |
含真实 API Key |
.muse/ 目录 |
含内部战略/开发状态 |
.agent/ 目录 |
含内部 Skill/Prompt |
.gemini/ 目录 |
含 AI 对话记录 |
memory/ / convo/ |
对话/记忆文件 |
*.pem / *.p12 / *.jks / *.key |
私钥/证书 |
禁止出现在代码中的 Key 模式
| 模式 | 服务 |
|---|---|
sk-[a-zA-Z0-9]{20,} |
OpenAI |
AIzaSy[a-zA-Z0-9_-]{33} |
Google/Gemini |
gsk_[a-zA-Z0-9]{20,} |
Groq |
sk_live_ / sk_test_[实际值] |
Stripe Secret |
pk_live_ / pk_test_[实际值] |
Stripe Publishable |
eyJhbGci[长JWT] |
JWT Token (Supabase/Vercel) |
AKIA[0-9A-Z]{16} |
AWS |
ghp_[a-zA-Z0-9]{36} |
GitHub PAT |
-----BEGIN (RSA )?PRIVATE KEY |
私钥 |
0x[a-fA-F0-9]{64} |
钱包私钥（注意：40位是地址，64位才是私钥） |
whsec_ |
Stripe Webhook Secret |
xoxb- / xoxp- |
Slack Token |
新项目 .gitignore 模板
新 repo 第一个 commit 前必须包含：
# Env files (NEVER commit real keys)
.env
.env.local
.env.*.local
.env.prod*
.env.vercel*
# Internal files
.muse/
.agent/
.gemini/
memory/
convo/
# Private keys
*.pem
*.p12
*.jks
*.key
# IDE
.idea/
.vscode/
# OS
.DS_Store
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.
- 7d ago First seen · 129 lines · 82 tokens per session scan A 2e4e0398a1ea
git-security-guard is a skill published in the GitHub repository myths-labs/muse (32 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,388 once invoked, about $0.0004 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 skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.
github-release-briefing-skill
Create a source-linked briefing for the latest published GitHub release of a public repository. Use for engineering teams tracking a dependency release; do not use it to publish releases or change repositories.
ijfw-ship
Use when the user says 'ship it', 'ship this', 'release', 'publish', 'launch', 'deploy', 'go live', 'wrap this up', 'time to ship', or invokes '/ijfw-ship'. Domain-aware release — software (test → tag → push → publish), book (final edit → format → KDP / agent / Substack), campaign (review → schedule → launch →…