An audit process for checking a GitHub repository’s CI/CD governance, meaning the rules that control builds, merges, deployments, and security checks.

It helps export branch protections, required checks, environment approvals, runner settings, security gates, and CODEOWNERS enforcement into an evidence report.

It shows where the repository’s live settings differ from its intended policies without changing the repository.

ci-audit — Skill for Claude Code by ivegamsft/basecoat

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.

Any agent

npx skills add ivegamsft/basecoat --skill ci-audit

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ivegamsft/basecoat/ci-audit/github.svg)](https://agentmods.dev/skills/ivegamsft/basecoat/ci-audit)

Your own site

<a href="https://agentmods.dev/skills/ivegamsft/basecoat/ci-audit"><img src="https://agentmods.dev/badge/skills/ivegamsft/basecoat/ci-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ivegamsft/basecoat/ci-audit"><img src="https://agentmods.dev/badge/skills/ivegamsft/basecoat/ci-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 520 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.00520
Opus 5.5	$0.00028	$0.00208
Sonnet 5.5	$0.00014	$0.00104
Haiku 4.5	$0.00007	$0.00052

Measured 1mo ago against content hash 3d02c8393f9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

skills/ci-audit/SKILL.md · 69 lines

What it actually says

CI/CD Audit Skill

Repository governance auditing for CI/CD controls using GitHub API/CLI evidence.

USE FOR

Exporting branch protection for main/master
Exporting required status checks
Reporting merge queue enabled/disabled state
Exporting GitHub Environment protection rules and production reviewers
Exporting allowed workflow-dispatch actors
Exporting runner groups and runner labels
Verifying required security scanning gates
Determining whether CODEOWNERS enforcement is active
Producing policy-vs-live gap analysis with remediation priorities

DO NOT USE FOR

Writing application code or feature implementations
Creating GitHub Actions workflows from scratch
Infrastructure-as-code implementation tasks
Changing repository settings or files during audit
General code review tasks unrelated to governance evidence

Templates in This Skill

Template	Purpose
`audit-findings-template.md`	Structured template for documenting audit findings with severity, category, and evidence
`recommendations-template.md`	Template for audit recommendations with priority, effort estimate, and expected ROI

References in This Skill

Reference	When to use
`ci-audit-checklist.md`	Comprehensive checklist covering all audit categories; use to validate audit completeness

Scripts in This Skill

scripts/ci-audit.ps1 — collects live governance evidence (branch protection, required checks, merge queue, environments, runners) via the GitHub CLI and emits the evidence pack sections.

Use with ci-audit agent for end-to-end auditing workflows. Route remediation to devops-engineer agent for implementation guidance.

Output contract

Produce markdown only:

Scope and timestamp
Evidence table for the 10 required governance sections
Gap matrix: policy expectation vs live setting
Prioritized remediation recommendations
Appendix with commands/endpoints used

Files

What ships with it

4 files 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.

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.

1mo ago Changed · +6 lines 3d02c8393f9c
1mo ago First seen · 63 lines · 71 tokens per session scan A 9077f6571779

Subscribe to this mod's changes

ci-audit is a skill published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 520 once invoked, about $0.0003 per session on Opus 5.5. 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.

CI and CD DevOps and cloud Security operations

deploy-templates

Built-in deploy recipes and deploy targets. Use when a task asks you to set up or change a stage/preprod/prod deploy workflow, including the system's "Set up deploy" tasks.

makifbaysal/tasktrooper · 46 tokens

ci-cd-pipeline-builder

Expert guide for building CI/CD pipelines with GitHub Actions, Vercel, and other platforms. Use when automating builds, tests, deployments, or release workflows.

eddiebelaval/squire · 41 tokens

deploy-staging

Despliega el proyecto a staging: verifica branch, identifica método de deploy (CI/CD o script), ejecuta y reporta status. No deploya prod sin confirmación.

SebastianLuser/claude-code-arcane · 40 tokens

remote-ops

Manage remote operations, infrastructure tasks, deployment procedures, and server administration. Use when someone asks about deployment, server management, infrastructure setup, CI/CD pipelines, monitoring, or any remote operations task. Triggers on "deploy", "server", "infrastructure", "ops", "pipeline"…

gyanranjan/polyagent-skills · 66 tokens

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

atmos-profiles

Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.

cloudposse/atmos · 35 tokens