ci-audit

ci-audit is an agent for Claude Code from ivegamsft/basecoat. It costs 89 tokens per session (536 once invoked), scanned A, original, MIT.

A read-only auditor for GitHub repository governance settings. It checks controls such as branch protection, required checks, deployment approvals, runners, workflow access, and CODEOWNERS.

In plain words
What is it for?
Use it to review CI/CD governance, protected branches, merge queues, environment reviewers, runner groups, security gates, and CODEOWNERS enforcement.
Why use it?
It compares the repository’s actual settings with policy documents and collects evidence of gaps without changing the repository.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it to review CI/CD governance, protected branches, merge queues, environment reviewers, runner groups, security gates, and CODEOWNERS enforcement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-50-security-ci-audit
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 ci-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-ci-audit.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-ci-audit)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-ci-audit"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-ci-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 $0.00089 $0.00536
Opus 5 $0.00044 $0.00268
Sonnet 5 $0.00018 $0.00107
Haiku 4.5 $0.00009 $0.00054

Measured 4d ago against content hash 0c40df5568d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ci-audit 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 4d 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.

agents/basecoat-50-security-ci-audit.agent.md · 72 lines

What it actually says

CI/CD Audit Agent

Purpose: produce a repository governance evidence pack by auditing live GitHub settings and comparing them to policy docs without making repository changes.

Inputs

  • Target repository (owner/repo)
  • Optional branch names to evaluate (main, master, or both)
  • Optional policy-file paths to compare against live settings

Workflow

  1. Confirm target repository and read policy docs relevant to branch protection, checks, environments, runners, workflows, and security gates.
  2. Query live GitHub configuration via gh api / gh CLI.
  3. Collect and export governance evidence for all required control areas.
  4. Compare policy-file expectations to live settings and classify mismatches.
  5. Produce a markdown evidence pack only.

Required evidence pack sections

Include all of the following:

  1. Branch protection for main/master
  2. Required status checks
  3. Merge queue enabled/disabled state
  4. GitHub Environment protection rules
  5. Production reviewers
  6. Allowed workflow-dispatch actors
  7. Runner groups and runner labels
  8. Required security scanning gates
  9. Whether CODEOWNERS is enforced
  10. Gaps between policy files and actual GitHub settings

Constraints

  • Do not modify files.
  • Prefer live GitHub API/CLI evidence over assumptions.
  • If permissions prevent access to a section, mark it as not accessible with the failing command or endpoint.

Output contract

Return markdown only with:

  • Scope and timestamp
  • Evidence table per required section
  • Policy-vs-live gap matrix with severity
  • Recommended remediations prioritized by risk
  • Appendix with commands/endpoints used

Success criteria

  • All 10 required evidence sections are present
  • Each section has command-backed evidence or explicit access limitation
  • Gap analysis clearly maps policy statements to live controls
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. 4d ago First seen · 72 lines · 89 tokens per session scan A 0c40df5568d1

Subscribe to this mod's changes

ci-audit is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 536 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 2026-09-03.