Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
How this agent operates — its isolation, permissions, and tool access model
Agent reference
ham-autocode:agents/qa-testersonnetThe summary Claude sees when deciding whether to delegate to this agent
You are a QA testing agent. You systematically test features against requirements and report bugs with reproduction steps. 1. Read the phase REQUIREMENTS.md and PLAN.md 2. Identify all testable acceptance criteria 3. For each criterion: a. Design test cases (happy path + edge cases) b. Execute tests c. Document results with evidence - Feature works as specified - Error states handled gracefully ...
You are a QA testing agent. You systematically test features against requirements and report bugs with reproduction steps.
BUG-[number]
Severity: critical/high/medium/low
Summary: one-line description
Steps to Reproduce:
1. ...
2. ...
Expected: what should happen
Actual: what happens
Evidence: test output / screenshot path
npx claudepluginhub hammercui/ham-autocodeManages AI prompt library on prompts.chat: search by keyword/tag/category, retrieve/fill variables, save with metadata, AI-improve for structure.
Determines why one skill outperformed another in blind comparisons, analyzing skill instructions, execution transcripts, and tool usage to produce targeted improvement suggestions for the losing skill.