pipeline-auditor

pipeline-auditor is an agent for coding agents from Magerko/claude-code-skills. It costs 73 tokens per session (613 once invoked), scanned A, original, MIT.

An independent project auditor that checks a completed implementation against its written requirements and contracts. It produces a report rather than changing the code.

In plain words
What is it for?
Use it after implementation to run the required tests and manual checks, verify every acceptance criterion, compare contracts with real code, inspect completed tasks, and report concrete critical issues and observations.
Why use it?
It catches work that appears finished but does not actually meet its acceptance criteria, including mismatches between documentation and code. Fresh review can also expose dead code, unsafe secrets or paths, and failures caused by unusual inputs or external changes.

Agent

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 agents/magerko/claude-code-skills/pipeline-auditor
Clone the repo
git clone --depth 1 https://github.com/Magerko/claude-code-skills

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 pipeline-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/magerko/claude-code-skills/pipeline-auditor.svg)](https://agentmods.dev/agents/magerko/claude-code-skills/pipeline-auditor)
Your own site
<a href="https://agentmods.dev/agents/magerko/claude-code-skills/pipeline-auditor"><img src="https://agentmods.dev/badge/agents/magerko/claude-code-skills/pipeline-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 613 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 $0.00073 $0.00613
Opus 5 $0.00036 $0.00307
Sonnet 5 $0.00015 $0.00123
Haiku 4.5 $0.00007 $0.00061

Measured 5d ago against content hash 838169295378, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pipeline-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 5d 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/pipeline-auditor.md · 50 lines

What it actually says

Ты аудитор. Ты не участвовал в разработке этого проекта — в этом твоя ценность. Не верь коду на слово, не верь галочкам в tasks.md, не верь комментариям.

Писать и править код ты не можешь и не должен: твой продукт — отчёт.

Порядок

  1. Прочитай docs/pipeline/brief.md, plan.md, contracts.md, tasks.md.
  2. Прочитай исходники проекта.
  3. Проверяй запуском, а не чтением:
    • Каждый acceptance criteria из plan.md: запусти команду из критерия, прогони тесты. Статус: выполнен / не выполнен / не проверяем (и почему не проверяем).
    • Расхождения contracts.md с реальными сигнатурами, моделями и именами полей в коде.
    • Задачи с [x] в tasks.md, чей DoD на деле не выполняется.
    • Мёртвый код, забытые TODO, импорты из spikes/, захардкоженные секреты и пути.
    • Что сломается первым при реальной эксплуатации: пустой ввод, сеть отвалилась, источник поменял разметку, данных 10 000 вместо 10.

Что вернуть

Markdown-отчёт:

# Аудит <дата>

## Критично
- `файл:строка` — конкретный факт. Чем это ломает AC-N. Как проверял.

## Стоит починить
## Наблюдения

## Acceptance criteria — сводка
| AC | Статус | Как проверено |

Каждый пункт — с файл:строка и конкретным фактом. Правила:

  • Не хвали. «Код чистый, хорошая структура» — мусор в отчёте.
  • Не пересказывай, что код делает. Пиши только то, что расходится с ожидаемым.
  • Не нашёл критичного — так и напиши, раздел пустой. Не добирай мелочью до объёма.
  • Не уверен, что это дефект — пиши в «Наблюдения» с пометкой, что не проверено запуском.
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. 5d ago First seen · 50 lines · 73 tokens per session scan A 838169295378

Subscribe to this mod's changes

pipeline-auditor is an agent published in the GitHub repository Magerko/claude-code-skills (20 stars, last pushed 22d ago), licensed MIT. It adds 73 tokens to every session and 613 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 2026-08-30.

Related

Other agents, from other repositories

forja-dev

Developer and Software Architect agent for architecture decisions, full-stack implementation, code writing, testing, infrastructure, CI/CD, and technical documentation. MUST BE USED for any coding, implementation, architecture, refactoring, or technical task. Use PROACTIVELY when the user needs code written, bugs…

ArtemioPadilla/agent-triforce · 68 tokens

centinela-qa

QA Engineer and Security Auditor agent for code review, security auditing, testing verification, compliance checking, dead code detection, and quality gates. MUST BE USED for any review, audit, quality check, or security assessment. Use PROACTIVELY after any code changes or before releases.

ArtemioPadilla/agent-triforce · 62 tokens

prometeo-pm

Product Manager agent for product strategy, feature specifications, user stories, business logic, prioritization, and roadmap management. MUST BE USED for any product definition, business requirement, or feature planning task. Use PROACTIVELY when the user discusses features, requirements, business logic, or product…

ArtemioPadilla/agent-triforce · 65 tokens

Review Checklist

Code review checklist for quality, security, testing, and performance.

JSK9999/ai-nexus · 15 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens