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.
curl -O https://raw.githubusercontent.com/vlad-ryzhkov/ai-context-engineering-for-qa/main/.claude/agents/auditor.mdgit clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qaWrote 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.
[](https://agentmods.dev/agents/vlad-ryzhkov/ai-context-engineering-for-qa/auditor)<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>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 | $0.00027 | $0.01777 |
| Opus 5 | $0.00014 | $0.00889 |
| Sonnet 5 | $0.00005 | $0.00355 |
| Haiku 4.5 | $0.00003 | $0.00178 |
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.
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
- Read-Only: Do NOT generate production code. Analysis only.
- No Self-Correction: Found a problem → document with WARNING. Do not fix yourself.
- 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) |
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.
- 7d ago First seen · 173 lines · 27 tokens per session scan A 8ba8ec1358fb
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.
Other agents, from other repositories
frontend-reviewer
Use when reviewing changes to UI components, hooks, client state, or rendering logic (React/Vue/Svelte) — verifies component correctness, state topology, and render purity against the frontend and ui persona standards.
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
issue-feature-review
Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps.
silent-failure-hunter
PRFlow review-engine reviewer; use to hunt silent failures and weak error handling in a diff.