auditar-release

auditar-release is a command for Claude Code from luanpdd/kit-mcp. It costs 48 tokens per session (1,162 once invoked), scanned A, original, MIT.

An audit of a release pipeline, the automated process that builds, checks, and delivers software.

In plain words
What is it for?
Review CI/CD in three areas—hermeticity, reproducibility, and policy enforcement—and prioritize fixes.
Why use it?
It exposes weaknesses in repeatability, isolated builds, and enforcement of delivery policies before they affect releases.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

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.

agentmods
npx agentmods add commands/luanpdd/kit-mcp/auditar-release
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

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 auditar-release

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/auditar-release.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/auditar-release)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/auditar-release"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/auditar-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.01162
Opus 5 $0.00024 $0.00581
Sonnet 5 $0.00010 $0.00232
Haiku 4.5 $0.00005 $0.00116

Measured 2d ago against content hash c1c66b4bcdbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

auditar-release 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 2d 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.

kit/commands/auditar-release.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cria/Atualiza:

  • .planning/RELEASE-AUDIT.md — relatório scored 30 pontos com top 5 fixes priorizados

Após: o user vê fragility quantificada (não opinião). Resultado feeds PRR Axe 5 (Change Management) v1.10 e gate release-pipeline-policy opt-in.

Exemplos:

/auditar-release                                          # full audit (3 dims)
/auditar-release --dimensions hermeticidade               # só hermeticidade
/auditar-release --gh-repo myorg/myrepo                   # override repo

Pré-requisitos opcionais:

  • gh CLI autenticado (gh auth status) — para checks de branch protection via API
  • Sem gh: agent skip dimension policy-enforcement parcialmente (filesystem only)

1. Parsear argumentos

DIMENSIONS=$(echo "$ARGUMENTS" | grep -oE -- '--dimensions [^ ]+' | awk '{print $2}')
GH_REPO=$(echo "$ARGUMENTS" | grep -oE -- '--gh-repo [^ ]+' | awk '{print $2}')
OUTPUT_PATH=$(echo "$ARGUMENTS" | grep -oE -- '--output [^ ]+' | awk '{print $2}')

[ -z "$OUTPUT_PATH" ] && OUTPUT_PATH=".planning/RELEASE-AUDIT.md"
mkdir -p "$(dirname "$OUTPUT_PATH")"

2. Dispatch para release-pipeline-auditor

Task(
  subagent_type="release-pipeline-auditor",
  prompt="
project_root: .
output_path: ${OUTPUT_PATH}
${DIMENSIONS:+dimensions: ${DIMENSIONS}}
${GH_REPO:+gh_repo: ${GH_REPO}}

Aplicar skills hermetic-builds + release-engineering. Etapas:
1. Detectar lockfile, CI files, Dockerfile
2. Auditar Hermeticidade (10pts): lockfile commitado, frozen-install, image SHA, sem network, SLSA provenance
3. Auditar Reprodutibilidade (10pts): actions pinned, node version pinned, package manager pinned, sem timestamps, build cache
4. Auditar Policy Enforcement (10pts): branch protection, required PR + reviewers + status checks, CODEOWNERS, signed commits, workflow permissions, release via tag
5. Score agregado (0-30) com veredito ROBUST/ADEQUATE/FRAGILE/BROKEN
6. Top 5 fixes priorizados com esforço estimado
"
)

Read the full file on GitHub · 110 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. 2d ago First seen · 110 lines · 48 tokens per session scan A c1c66b4bcdbc

Subscribe to this mod's changes

auditar-release is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 1,162 once invoked, about $0.0002 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.