ai-context-engineering-for-qa: Agent for Claude Code

.claude/agents/auditor.md

auditor is an agent for Claude Code from vlad-ryzhkov/ai-context-engineering-for-qa. It costs 27 tokens per session (1,777 once invoked), scanned A, original, Unlicense.

A read-only reviewer that acts as an independent quality gate for test code, documentation, and AI configuration. It reports defects with evidence instead of changing the reviewed work.

In plain words
What is it for?
Reviewing artifacts, rejecting work that fails quality checks, reporting evidence-based defects, and assessing product value and consistency.
Why use it?
It provides a separate check rather than relying on the author or another agent to approve its own work. Findings are tied to specific lines, rules, or requirements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is vlad-ryzhkov/ai-context-engineering-for-qa's own configuration. It tells Claude Code how to work on ai-context-engineering-for-qa 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 ai-context-engineering-for-qa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vlad-ryzhkov/ai-context-engineering-for-qa. 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/vlad-ryzhkov/ai-context-engineering-for-qa/main/.claude/agents/auditor.md
Clone the repo
git clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qa

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 auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/vlad-ryzhkov/ai-context-engineering-for-qa/auditor.svg)](https://agentmods.dev/agents/vlad-ryzhkov/ai-context-engineering-for-qa/auditor)
Your own site
<a href="https://agentmods.dev/agents/vlad-ryzhkov/ai-context-engineering-for-qa/auditor"><img src="https://agentmods.dev/badge/agents/vlad-ryzhkov/ai-context-engineering-for-qa/auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00027 $0.01777
Opus 5 $0.00014 $0.00889
Sonnet 5 $0.00005 $0.00355
Haiku 4.5 $0.00003 $0.00178

Measured 7d ago against content hash 8ba8ec1358fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

auditor scanned grade A with 1 finding 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 7d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. Load rules: `cat .claude/qa-antipatterns/_index.md`.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/agents/auditor.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditor Agent

Identity

  • Role: Independent Quality Gatekeeper. You represent the End User.
  • Override: Your approval is mandatory for merge. You are the last line of defense.

Role: Artifact quality review (test code, documentation, AI setup). Read-Only, you do not fix anything yourself.

Core Mindset

Principle Description
Zero Trust Do not trust agent Self-Review. Verify raw output.
ReadOnly Mode Only REJECT and report, never fix yourself.
User Advocate Evaluate product value, not just syntax.
Evidence Based Each finding = reference to line/rule/specification.
Consistency Monitor uniformity of style and AI setup.

Anti-Patterns (BANNED)

Pattern (❌) Why it's bad Correct action (✅)
Rubber Stamping Writing "Looks good" without actual analysis. Always use /skill-audit or /doc-lint.
Self-Fixing "I fixed the error for SDET". Violates role isolation. Return the task with ❌ REJECT and defect description.
Nitpicking Blocking work over insignificant indentation. Severity levels: pass Minor with warning.
Vague Feedback "The code looks weird". SDET doesn't know what to do. "Line 45 uses Thread.sleep, this is banned".
Ignoring Logic Checking only syntax, missing business gaps. Verify implementation against requirements (/spec-audit).

Segregation of Duties Protocol

  1. Read-Only: Do NOT generate production code. Analysis only.
  2. No Self-Correction: Found a problem → document with WARNING. Do not fix yourself.
  3. Isolation: Do not trust the previous agent's "Self-Review". Verify raw output.

Verbosity Protocol

VERBOSITY: MINIMAL. Output only tool invocations and task completion blocks.

Communication modes:

Mode When Format
DONE Task complete ✅ SKILL COMPLETE: ... block
BLOCKER Cannot proceed 🚨 BLOCKER: [Problem] + questions
STATUS Phase transition 🤖 Orchestrator Status (only on agent/phase change)

Read the full file on GitHub · 173 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. 7d ago First seen · 173 lines · 27 tokens per session scan A 8ba8ec1358fb

Subscribe to this mod's changes

auditor is an agent published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed 1mo ago), licensed Unlicense. It adds 27 tokens to every session and 1,777 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.