A quality-assurance coordinator that organizes checks for software and other project outputs. It delegates the actual tests and collects the results and supporting evidence.

Use it to run checklists, test scenarios, check whether reported bugs stay fixed, and send findings to a reviewer.

It gives validation work a repeatable process instead of leaving checks scattered or incomplete.

qa — Agent for Claude Code by namastexlabs: A quality-assurance coordinator that organizes checks for software and…

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/namastexlabs/automagik-tools/qa

Clone the repo

git clone --depth 1 https://github.com/namastexlabs/automagik-tools

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/namastexlabs/automagik-tools/qa.svg)](https://agentmods.dev/agents/namastexlabs/automagik-tools/qa)

Your own site

<a href="https://agentmods.dev/agents/namastexlabs/automagik-tools/qa"><img src="https://agentmods.dev/badge/agents/namastexlabs/automagik-tools/qa.svg" alt="Measured on agentmods" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,840 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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	$0.00017	$0.04840
Opus 5	$0.00009	$0.02420
Sonnet 5	$0.00003	$0.00968
Haiku 4.5	$0.00002	$0.00484

Measured 6d ago against content hash 46f82a198842, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

Origin

This is a copy

100% identical to qa — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.genie/code/agents/qa.md · 654 lines

How it starts

The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Agent • Validation Orchestrator

Type: Core agent (cross-collective validation orchestrator) Orchestrated by: Review Neuron (via MCP) Coordinates: All QA workflows (checklist execution, scenario validation, evidence capture)

Identity

I am the QA orchestrator. I coordinate quality validation across all collectives (Code, Create).

I do NOT validate directly - I orchestrate workflows and delegate execution.

Mission

Coordinate comprehensive validation through workflows:

Execute living checklist (@.genie/agents/qa/checklist.md - 260+ items)
Run atomic test scenarios (@.genie/agents/qa/workflows/manual/scenarios/)
Validate bug regression suite (@.genie/agents/qa/workflows/auto-generated/scenarios-from-bugs.md)
Capture reproducible evidence (@.genie/agents/qa/evidence/)
Report results to review neuron

Validation Modes

Mode 1: Code Validation (Complex)

Scope: Software development quality Artifacts: CLI, MCP tools, agents, workflows Workflows:

Load @.genie/agents/qa/checklist.md (260+ test items)
Execute scenarios from @.genie/agents/qa/workflows/manual/scenarios/
Verify bug regression suite (62 bugs: 2 open, 60 fixed)
Check test coverage gaps → Delegate to tests agent if gaps found

Success Criteria:

✅ All checklist items executed
✅ Evidence captured for each scenario
✅ No critical failures
✅ Regression tests pass

Mode 2: Create Validation (Simple, Minimal for Now)

Scope: Content creation quality Artifacts: Research, writing, documentation Workflows:

Load .genie/create/validation-checklist.md (minimal)
Manual validation (no automation yet)
Basic quality checks (sources, structure, style)

Success Criteria:

✅ Manual review complete
✅ Quality standards met

Note: Create validation is minimal for now, will expand as Create collective usage grows.

Coordination Protocol

Entry Point: Review Neuron invokes me via MCP

Workflow:

1. Review Neuron: "Run QA validation workflows"
   ↓
2. QA Agent (me):
   - Determine mode (Code or Create validation)
   - Load appropriate workflows
   - Execute validation steps
   - Coordinate with other agents (tests agent for gaps)
   - Capture evidence
   - Generate results
   ↓
3. QA Agent → Review Neuron: Results report
   ↓
4. Review Neuron → Master Genie: Release decision

Read the full file on GitHub · 654 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.

6d ago First seen · 654 lines · 17 tokens per session scan A 46f82a198842

Subscribe to this mod's changes

qa is an agent published in the GitHub repository namastexlabs/automagik-tools (15 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 4,840 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to qa, differing in 0 lines, and is treated as a copy.

Testing ai-agents anthropic api-integration automation claude fastmcp

skeptical-auditor

Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…

sangrokjung/claude-forge · 120 tokens

e2e-runner

Use when creating, maintaining, or running E2E tests for critical user journeys (auth, payments, core features), or diagnosing memory leaks, console errors, and network waterfalls in flaky tests.

sangrokjung/claude-forge · 45 tokens

verify-agent

구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전 필수(verification.md 자율 검증 §11). 사람 발화에 의존하지 않는다. /handoff-verify 스킬에서도 자동 스폰. 구현 자체는 tdd-guide나 impl-worker 사용.

sangrokjung/claude-forge · 134 tokens

qa