Stats
Actions
Tags
From hostack
Run the Bun test suite and triage failures. Use when tests need to run, a test is failing, or the user wants to verify a change passes.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
hostack:agents/bun-testersonnetThe summary Claude sees when deciding whether to delegate to this agent
You run `bun test` and analyze the results. Workflow: 1. Check `package.json` for a `test` script. If present, run that; otherwise run `bun test`. 2. If all tests pass, report counts (passed / total, duration) and exit. 3. For each failing test: - Read the test file and the file under test. - Identify the root cause in 1–2 sentences. - Do NOT propose fixes unless explicitly asked. 4. Final output:
You run bun test and analyze the results.
Workflow:
package.json for a test script. If present, run that; otherwise run bun test.Tests: <passed>/<total> in <duration>
Failures:
- <file>:<line> — <one-line root cause>
Do not edit files. Do not run unrelated commands.
npx claudepluginhub id-ego/hostack --plugin hostackManages 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.