agent-threat-rules: Command for Claude Code

.claude/commands/scan-famous.md

scan-famous is a command for Claude Code from Agent-Threat-Rule/agent-threat-rules. It costs 0 tokens per session (367 once invoked), scanned A, original, MIT.

A command for scanning a list of popular MCP skills, ranked by public star counts, for security problems.

In plain words
What is it for?
It is for selecting packages to audit, running their security checks, preparing English and Chinese reports for high-risk results, and marking clean popular packages as potentially safe.
Why use it?
It helps focus security review on widely used packages and explains serious findings before they are shared publicly.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Agent-Threat-Rule/agent-threat-rules's own configuration. It tells Claude Code how to work on agent-threat-rules itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-threat-rules configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/user/Downloads/agent-threat-rules.

Reuse

Borrowing it

Nothing to install: this file belongs to Agent-Threat-Rule/agent-threat-rules. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Agent-Threat-Rule/agent-threat-rules/main/.claude/commands/scan-famous.md
Clone the repo
git clone --depth 1 https://github.com/Agent-Threat-Rule/agent-threat-rules

Made for: Claude Code.

Wrote 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.

agentmods badge for scan-famous

README.md
[![agentmods](https://agentmods.dev/badge/commands/agent-threat-rule/agent-threat-rules/scan-famous/github.svg)](https://agentmods.dev/commands/agent-threat-rule/agent-threat-rules/scan-famous)
Your own site
<a href="https://agentmods.dev/commands/agent-threat-rule/agent-threat-rules/scan-famous"><img src="https://agentmods.dev/badge/commands/agent-threat-rule/agent-threat-rules/scan-famous/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.

agentmods 80×15 button for scan-famous

Your own site · 80×15
<a href="https://agentmods.dev/commands/agent-threat-rule/agent-threat-rules/scan-famous"><img src="https://agentmods.dev/badge/commands/agent-threat-rule/agent-threat-rules/scan-famous.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00367
Opus 5 $0.00000 $0.00183
Sonnet 5 $0.00000 $0.00073
Haiku 4.5 $0.00000 $0.00037

Measured 10d ago against content hash f56616566bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

scan-famous 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 10d 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.

.claude/commands/scan-famous.md · 37 lines

What it actually says

Scan Famous / High-Star MCP Skills

Scan the most popular MCP skills to find issues in well-known packages. This is the highest-value content for Skills Sec.

Steps

  1. Load the registry and sort by stars:
cd /Users/user/Downloads/agent-threat-rules
node -e "
const r = require('./mcp-registry.json');
const top = r.entries
  .filter(e => e.stars && e.stars > 50)
  .sort((a,b) => b.stars - a.stars)
  .slice(0, 30);
top.forEach((e,i) => console.log((i+1) + '. [' + (e.stars||0) + ' stars] ' + e.name + ' — ' + (e.description||'').slice(0,80)));
"
  1. Show the top 30 by stars. Ask which ones to scan (or scan all).

  2. For each selected skill, run the full audit pipeline:

    • npm pack → extract → ATR scan → AST analysis → verdict
  3. For any CRITICAL or HIGH results:

    • Present findings using T1 (Famous Skill Expose) template
    • Fill in all template variables with real data
    • Generate both EN and ZH versions
    • Responsible disclosure reminder: "72-hour window — notify author first?"
    • Ask: approve post or edit?
  4. For CLEAN results with many stars:

    • Note as "verified safe" — potential whitelist entry
    • Generate a positive post: "{SKILL_NAME} ({STARS} stars) — scanned clean. Safe to use."
  5. Summary: N scanned, N CRITICAL, N HIGH, N CLEAN, N posts generated

Changes

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.

  1. 10d ago First seen · 37 lines · 0 tokens per session scan A f56616566bf6

Subscribe to this mod's changes

scan-famous is a command published in the GitHub repository Agent-Threat-Rule/agent-threat-rules (388 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 367 tokens. 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.