claude

qa-cycle

Whole-app QA by a team of Claude Code agents: maps every feature, tests each one in parallel, lists the bugs for your approval, fixes them in isolated git worktrees and has a fresh agent verify every fix, cycle after cycle. Also ships /regression and /manual-qa for checking a single change.

3 on GitHubby Max Shwedv1.2.5MITupdated 6 days agotesting
/

Plugin qa-cycle from marketplace qa-cycle in DrunkenDealer/claude-code-qa-cycle. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (3)

  • manual-qa

    Manual-QA pass over recent changes — files concrete bug reports (blocker/major/minor) for UI, navigation, and cross-feature regressions a tester would catch. Auto-detects the platform (Android, iOS, web) from the changed files and audits against that platform's bar; off-platform changes are judged a

  • qa-cycle

    Whole-app QA loop run by an orchestrator — map every feature, plan small test units, fan out one tester agent per unit, return findings as a list, then after the user's go-ahead fan out fixers (worktrees) and fresh verifiers (sandboxes), and loop cycle after cycle until every fix-now item is verifie

  • regression

    Post-feature verification gate — phase 1 reviews the code (bugs, pitfalls, code smells), phase 2 plays manual tester — it builds and runs the project's test suite on every platform, walks the blast radius, audits against the platform bar, and optionally drives an emulator, simulator or browser when

Subagents (5)

  • qa-fixer

    QA-cycle fixer — executes one fix in its own git worktree, from a qa-planner plan or (for simple local items) straight from the orchestrator's brief. Stops with PLAN GAP instead of redesigning. Run with worktree isolation.

  • qa-mapper

    QA-cycle mapper — reads the code and builds the feature map (entry points → features → states → cross-feature flows → integrations) that the unit plan is cut from. Read-only. Use at step 1 of a QA cycle, or to refresh the map after big changes.

  • qa-planner

    QA-cycle planner — reads the code for one finding (or a failed fix) and writes the fix plan a qa-fixer executes. Read-only. Use for fixes touching state, history, concurrency or persisted data, and to revise a plan after a failed verification or a PLAN GAP.

  • qa-tester

    QA-cycle tester — runs ONE test unit against current main in its own sandbox, drives the app like a user, reproduces every finding twice and reports it in the tracker format. Never fixes anything.

  • qa-verifier

    QA-cycle verifier — fresh eyes on one merged fix, in its own sandbox of current main. Adversarial: original repro, variants, every intermediate step, nearby regressions. Never the agent that wrote the fix.

View source on GitHub mashlab.app

Similar plugins

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling

19 skills

anthropics/skills 193,780

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

1 command · 6 agents

anthropics/claude-code 155,476

storybook

claudecodex

Build, preview, and test UI components with Storybook.

7 skills

storybookjs/storybook 91,552

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain qa-cycle?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted