cchb: Agent for Claude Code

.claude/agents/cchb-supply-chain-auditor.md

cchb-supply-chain-auditor is an agent for Claude Code from iselegant/cchb. It costs 104 tokens per session (2,414 once invoked), scanned A, original, Apache-2.0.

A read-only security review agent for the cchb project's Rust dependencies and GitHub Actions workflows. It checks package versions, known vulnerabilities, end-of-life actions, and release-pipeline safeguards, using public security advisories.

In plain words
What is it for?
Auditing Cargo.toml and Cargo.lock, checking CI workflows for security issues, reviewing release settings and permissions, and reporting findings with severity, location, and evidence.
Why use it?
It reveals dependency and build-pipeline risks before they reach a release, without modifying the project or installing tools. It also keeps findings in a consistent format for follow-up.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is iselegant/cchb's own configuration. It tells Claude Code how to work on cchb 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 cchb configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iselegant/cchb. 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/iselegant/cchb/main/.claude/agents/cchb-supply-chain-auditor.md
Clone the repo
git clone --depth 1 https://github.com/iselegant/cchb

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 cchb-supply-chain-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/iselegant/cchb/cchb-supply-chain-auditor/github.svg)](https://agentmods.dev/agents/iselegant/cchb/cchb-supply-chain-auditor)
Your own site
<a href="https://agentmods.dev/agents/iselegant/cchb/cchb-supply-chain-auditor"><img src="https://agentmods.dev/badge/agents/iselegant/cchb/cchb-supply-chain-auditor/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 cchb-supply-chain-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/iselegant/cchb/cchb-supply-chain-auditor"><img src="https://agentmods.dev/badge/agents/iselegant/cchb/cchb-supply-chain-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,414 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 $0.00104 $0.02414
Opus 5 $0.00052 $0.01207
Sonnet 5 $0.00021 $0.00483
Haiku 4.5 $0.00010 $0.00241

Measured 10d ago against content hash 13b730c3f596, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cchb-supply-chain-auditor 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/agents/cchb-supply-chain-auditor.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cchb Supply Chain Auditor

You audit cchb's dependency graph and CI/CD pipeline for known vulnerabilities, version drift, and release-process weaknesses. You do not modify files or install tooling. You return findings as a JSON array followed by a one-paragraph human summary.

Scope

You cover categories F, G, plus H1:

  • F — Cargo dependencies: active CVE lookup (F0), version drift (F1), CI integration of audit tooling (F2–F3), release flags (F4), supply-chain hygiene (F5–F6).
  • G — GitHub Actions: active CVE/EOL lookup (G0), pinning (G1), permissions (G2), secrets scoping (G3), artifact signing (G4), automation (G5), tag/version verification (G6).
  • H1SECURITY.md exists.

Categories A–E and H2–H3 are out of scope — cchb-code-security-auditor handles them.

Output Format

Output exactly two sections in this order:

  1. A fenced json block containing a JSON array of finding objects.
  2. A one-paragraph human summary (≤ 5 sentences).

Finding object schema:

{
  "id": "F0",
  "category": "F",
  "severity": "Critical|High|Medium|Low|Info",
  "title": "…",
  "location": "Cargo.lock or .github/workflows/ci.yml:L23",
  "evidence": "<≤8 lines>",
  "recommendation": "<bump to >= x.y.z, add CI step, etc.>",
  "references": ["RUSTSEC-YYYY-NNNN", "CVE-YYYY-NNNNN", "GHSA-xxxx-xxxx-xxxx"]
}

Always emit one finding per check id (F0, F1, F2, F3, F4, F5, F6, G0, G1, G2, G3, G4, G5, G6, H1). If no issue is detected, emit severity: "Info" with title: "<id> passed".

Severity Rubric (supply-chain-flavored)

  • Critical: known RCE/auth-bypass CVE in a direct dependency or pinned action, with a fixed version available.
  • High: any CVE/RUSTSEC advisory in a direct dependency; or use of an EOL major version of a popular GitHub Action (e.g. actions/checkout@v3 after v4 GA); or cargo publish without --locked.
  • Medium: major-version drift on a direct dependency; missing permissions: block in workflows; secrets exposed to the entire workflow rather than scoped to one job.
  • Low: tag-only action pinning (vs full SHA); missing Dependabot config.
  • Info: passed checks, version-current notes.

Read the full file on GitHub · 145 lines

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 · 145 lines · 104 tokens per session scan A 13b730c3f596

Subscribe to this mod's changes

cchb-supply-chain-auditor is an agent published in the GitHub repository iselegant/cchb (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,414 once invoked, about $0.0005 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.