qa Claude Code subagentA

qa from claude-genasis/genasis is a Claude Code subagent: a helper Claude Code hands a task to, with its own instructions.

Install it, pinned
mdr add claude-genasis/genasis/tests/golden/blank/expected/.claude/agents/qa.md@git:20260509.5977877

Pins git:20260509.5977877 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
Claude Code subagent
Repository
claude-genasis/genasis
Path
tests/golden/blank/expected/.claude/agents/qa.md
Versions recorded
1
Latest version
git:20260509.5977877, committed May 9, 2026
Size
390 bytes
Repository stars
7
License
MIT

M14 default qa role.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<!-- GENASIS:BEGIN role=qa version=1.0 hash=80ddc685 -->
## qa overlay
project: blank-fixture
<!-- GENASIS:END -->
# qa

Default base body for the qa role. The marker fence below this
line is owned by Genasis (`attach`/`upgrade` rewrites it). Anything
outside the fence is yours to edit.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add claude-genasis/genasis/tests/golden/blank/expected/.claude/agents/qa.md@sha256:861f2f1a28856944

The line at the top of this page pins the label git:20260509.5977877, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ukwbuiuvvlpjpkoa.svg)](https://markdownregistry.com/a/art_ukwbuiuvvlpjpkoa)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in claude-genasis/genasis/tests/golden/blank/expected/.claude/agents/qa.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of qa.md from somewhere else? Ask it: where did my qa.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on May 9, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260509.5977877 latest2026-05-09 5977877 390 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (390 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

claude-genasis/genasis · 7 stars · license MIT · pushed 2026-05-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ukwbuiuvvlpjpkoa
GET https://markdownregistry.com/api/v1/resolve?ref=claude-genasis/genasis/tests/golden/blank/expected/.claude/agents/qa.md
GET https://markdownregistry.com/api/v1/blob/861f2f1a288569448f6b7120d285b1bb85b48ae454087e29c80d7e052fc49870

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: which agent file does what.

More from claude-genasis/genasis

CLAUDE.md CLAUDE.md file
claude-genasis/genasis · CLAUDE.md
git:20260512.a75d9fb · audit A · 7 stars
architect Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/architect.md · M14 default architect role.
git:20260509.5977877 · audit A · 7 stars
backend Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/backend.md · M14 default backend role.
git:20260509.5977877 · audit A · 7 stars
code-reviewer Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/code-reviewer.md · M14 default code-reviewer role.
git:20260509.5977877 · audit A · 7 stars
designer Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/designer.md · M14 default designer role.
git:20260509.5977877 · audit A · 7 stars
devops Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/devops.md · M14 default devops role.
git:20260509.5977877 · audit A · 7 stars
frontend Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/frontend.md · M14 default frontend role.
git:20260509.5977877 · audit A · 7 stars
planner Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/planner.md · M14 default planner role.
git:20260509.5977877 · audit A · 7 stars
pm Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/pm.md · M14 default pm role.
git:20260509.5977877 · audit A · 7 stars
security Claude Code subagent
claude-genasis/genasis · tests/golden/blank/expected/.claude/agents/security.md · M14 default security role.
git:20260509.5977877 · audit A · 7 stars
backend Claude Code subagent
claude-genasis/genasis · tests/golden/ecc-only/input/.claude/agents/backend.md · Backend engineer agent (Hono, Drizzle, REST/RPC).
git:20260503.64dde80 · audit A · 7 stars
frontend Claude Code subagent
claude-genasis/genasis · tests/golden/ecc-only/input/.claude/agents/frontend.md · Frontend engineer agent (Next.js, React, Tailwind).
git:20260503.64dde80 · audit A · 7 stars

Every file in claude-genasis/genasis

Other files named qa

qa SKILL.md skill
garrytan/gstack · qa/SKILL.md · Use when you test the site, API or CLI and fix bugs. (gstack)
v2.0.0 · audit A · 141,854 stars
qa SKILL.md skill
q00/ouroboros · skills/qa/SKILL.md · General-purpose QA verdict for any artifact type
git:20261116.64a2b2e · audit A · 6,381 stars
qa SKILL.md skill
sipyourdrink-ltd/bernstein · templates/skills/qa/SKILL.md · Test writing - pytest suites, edge cases, regressions.
git:20260521.b455a7c · audit A · 1,214 stars
qa Claude Code subagent
agentworkforce/relay · .claude/agents/qa.md · Quality assurance, testing protocols, and defect management. Creates test plans and validates feature completeness.
git:20260814.67b52ca · audit A · 1,134 stars
qa SKILL.md skill
sethgammon/citadel · skills/qa/SKILL.md · Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user…
git:20260611.0f3f8e7 · audit B · 931 stars
qa SKILL.md skill
suboss87/fdeops · skills/qa/SKILL.md · Exercise the delivered customer journey using real runtime or browser evidence. Use for functional acceptance testing…
git:20261005.ed7f271 · audit A · 817 stars
qa SKILL.md skill
asymmetric-al/core · .agents/skills/qa/SKILL.md · Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores…
git:20260430.3022c5f · audit A · 370 stars
qa SKILL.md skill
arcee-ai/nac · .agents/skills/qa/SKILL.md · Run scalable, isolated live QA for nac development. In NAC orchestrator mode the top-level local orchestrator must…
git:20261102.1ac8f31 · audit A · 314 stars

Browse by kind, by grade A, or by owner.