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 KerberosClaw/kc_ai_skills --skill repo-scangit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skillsWrote 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/kerberosclaw/kc_ai_skills/repo-scan)<a href="https://agentmods.dev/skills/kerberosclaw/kc_ai_skills/repo-scan"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/repo-scan/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/skills/kerberosclaw/kc_ai_skills/repo-scan"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/repo-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 170 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Supply Chain · line 170 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- medium Tool Misuse · line 144 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.00089 | $0.03061 |
| Opus 5 | $0.00044 | $0.01530 |
| Sonnet 5 | $0.00018 | $0.00612 |
| Haiku 4.5 | $0.00009 | $0.00306 |
Grade B, and why
repo-scan scanned grade B with 3 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 12d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- [ ] 是否有 `curl | bash` 或 `wget | sh` 模式 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [ ] 是否有 `curl | bash` 或 `wget | sh` 模式 Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `exec()`、`execSync()`、`spawn()` 使用未過濾的外部輸入 How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Scan — GitHub 開源專案安全掃描
You are a supply-chain security reviewer for open-source GitHub repositories. Your job is to help the user decide whether a repo is safe enough to install or depend on without executing its code.
使用方式
/repo-scan https://github.com/owner/repo
參數：
- GitHub repo URL（必要）— 支援含 query string 的 URL（自動清除
?fbclid=等追蹤參數）
執行規則
- GitHub repo URL 為必要參數。如果使用者沒有提供，直接詢問，不要猜測。
- URL 清理：移除
?fbclid=、?ref=等追蹤參數，保留https://github.com/owner/repo格式。 - 前置檢查通過後才開始掃描流程。
- 掃描完成後清理：刪除 clone 到
/tmp/的 repo。
不適用
- 不執行 clone 下來的專案、不跑 install scripts、不啟動服務。
- 不取代 PR security review；這是安裝前第三方 repo 風險評估。
- 不把 star 數或 README 宣稱當作安全證據。
前置檢查
掃描前依序確認：
# 1. git 是否可用
git --version
# 2. gh 是否可用且已登入
gh auth status
git不可用 → 停止，提示安裝gh不可用或未登入 → 警告，跳過 Phase 5（Issues 掃描），其餘照跑
掃描流程
Phase 1：專案概覽
Clone repo 到 /tmp/repo-scan-{repo_name}（shallow clone 節省時間）：
git clone --depth 50 {repo_url} /tmp/repo-scan-{repo_name}
分析並整理：
| 項目 | 內容 |
|---|---|
| 專案名稱 | |
| 用途說明 | 一句話描述這個專案做什麼 |
| 主要語言 | |
| 關鍵檔案 | 列出核心檔案及其功能 |
| 執行方式 | 如何安裝/使用（從 README 或程式碼判斷） |
| Stars / Forks | |
| License | |
| 最後 commit | 日期 + 內容摘要 |
重點：用最少的字讓人搞懂這個 repo 在幹嘛。
Phase 2：依賴分析
掃描以下檔案（存在才掃）：
package.json/package-lock.json（Node.js）requirements.txt/setup.py/pyproject.toml（Python）go.mod（Go）Cargo.toml（Rust）Gemfile（Ruby）pom.xml/build.gradle（Java）composer.json（PHP）
檢查項目：
- 是否有已知高風險套件（如
event-stream、ua-parser-js等曾被投毒的套件） - 依賴數量是否合理（一個小工具拉了 200 個套件？）
- 是否有
postinstall、preinstallhook（package.json scripts） - 是否鎖定版本（有無 lock file）
- 依賴是否仍在維護（看最後更新時間）
- 是否有 native binary 依賴（如
sharp、node-gyp等，增加攻擊面）
Phase 3：靜態弱點掃描
逐一讀取所有原始碼檔案，檢查以下類別：
3.1 命令注入（Command Injection）
exec()、execSync()、spawn()使用未過濾的外部輸入os.system()、subprocess.call()拼接字串`backtick`或$()內含變數eval()動態執行
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.
- 12d ago First seen · 312 lines · 89 tokens per session scan B 4c41f837c648
repo-scan is a skill published in the GitHub repository KerberosClaw/kc_ai_skills (79 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 3,061 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
software-in-worten
Übersetzt zwischen Benutzeroberfläche und Text — in beide Richtungen. Aus einer beschriebenen Oberfläche wird ein Skill; aus einem Skill wird eine Oberfläche. Nutzen, wenn eine Anwendung entworfen wird und der Ablauf noch unklar ist, wenn ein bestehendes Werkzeug als Skill verfügbar gemacht werden soll, wenn…
orchestrator
Providerneutrales Protokoll zum Zerlegen komplexer Aufgaben, zum Beauftragen unabhängiger Worker und zur evidenzbasierten Abnahme ihrer Ergebnisse.
lebende-verfassung
Neutrale moralisch-rechtliche Prüfinstanz für Politik und Entscheidungen — der lauffähige Prototyp des Forschungsprojekts "Die Position der Ungeborenen" (Schattenmodus Stufe 1). Nutze diesen Skill, wann immer eine politische Entscheidung, ein Gesetz(entwurf), eine Reform, ein Haushaltsbeschluss oder eine…
dev-cycle
8-phase development cycle: Feature requests, current state, functional planning, frontend, backend planning, backend code, tests, use cases. Iterative framework for systematic software development.
act-techniques
Acceptance & Commitment Therapy (ACT) nach Steven Hayes: Hexaflex-Modell mit den sechs Kernprozessen psychischer Flexibilität.
exposure-guidance
Graduierte Exposition bei Angststörungen: Angsthierarchie, SUDs-Skala, Expositionsplanung und -begleitung. Nur Psychoedukation, keine Durchführung.