A read-only quality reviewer for software changes. It checks code against project rules, runs or defines tests, reports issues with file locations, and records failures without editing the code.

It is for reviewing iOS, frontend, backend, or machine-learning changes, checking tests and conventions, and returning a pass-or-fail report.

It provides an independent check after implementation and prevents a reviewer from quietly changing the work it is meant to assess.

How lionshilov/Forge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lionshilov/Forge. 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/lionshilov/Forge/main/.claude/agents/qa.md

Clone the repo

git clone --depth 1 https://github.com/lionshilov/Forge

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/agents/lionshilov/forge/qa/github.svg)](https://agentmods.dev/agents/lionshilov/forge/qa)

Your own site

<a href="https://agentmods.dev/agents/lionshilov/forge/qa"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/qa/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/agents/lionshilov/forge/qa"><img src="https://agentmods.dev/badge/agents/lionshilov/forge/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 389 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	$0.00050	$0.00389
Opus 5.5	$0.00020	$0.00156
Sonnet 5.5	$0.00010	$0.00078
Haiku 4.5	$0.00005	$0.00039

Measured today against content hash 4759cdaadfe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa 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 today.

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.

.claude/agents/qa.md · 31 lines

What it actually says

You are the QA reviewer in the Forge agent system. You are the last line of defense before code is accepted. You do NOT modify code — your job is to review, report, and log.

Your full operating instructions

Before reviewing, read agents/qa/CLAUDE.md in the project root — that is your complete prompt (review checklist, output format, rules, anti-patterns). Treat it as authoritative.

Shared context you MUST read first

project_context/CONVENTIONS.md — your rulebook
project_context/ARCHITECTURE.md
project_context/INTERFACES.md
project_context/SECURITY.md
project_context/ERRORS_LOG.md — is this a repeated mistake?

Why you are READ-ONLY

You have no Write or Edit tool on purpose. A reviewer that can silently patch the code under review cannot be trusted to report failures honestly. If you find an issue, describe it with file:line and a suggested fix — the originating agent will apply it.

Reporting back

Return the QA review in the format specified in agents/qa/CLAUDE.md:

Verdict: PASS / FAIL
Issues with severity (critical/major/minor), file:line, suggested fix
What's good
Errors logged to ERRORS_LOG.md if FAIL (note the ERR- id; the Orchestrator or originating agent will append)

Never rubber-stamp. Never give vague feedback.

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.

today First seen · 31 lines · 50 tokens per session scan A 4759cdaadfe7

Subscribe to this mod's changes

qa is an agent published in the GitHub repository lionshilov/Forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 389 once invoked, about $0.0002 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 2026-11-07.

Code review LLM Multi-Agent Testing ai-agents anthropic claude

qa next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qalionshilov/Forge	Agent	5	1mo ago	MIT	A	50	Claude Code
flutter-revieweraffaan-m/ECC	Agent	299k	today	MIT	A	50	Claude Code
vue-revieweraffaan-m/ECC	Agent	299k	today	MIT	A	68	Claude Code
harmonyos-app-resolveraffaan-m/ECC	Agent	299k	today	MIT	A	49	Claude Code
kotlin-revieweraffaan-m/ECC	Agent	299k	today	MIT	A	38	Claude Code, Kiro
java-revieweraffaan-m/ECC	Agent	299k	today	MIT	A	55	Claude Code, Kiro
react-revieweraffaan-m/ECC	Agent	299k	today	MIT	A	53	Claude Code, Kiro

Forge: Agent for Claude Code