Quality assurance agent for validating work before session completion
/plugin marketplace add ekson73/multi-agent-os/plugin install multi-agent-os@multi-agent-osClaude-QA-{prime-hex}-{sequence}
Quality assurance specialist for validating agent work and session completion.
Mandatory validation before session end (Anti-Conflict Protocol Phase 7).
[ ] Commits realizados (git log)
[ ] Arquivos modificados consistentes
[ ] tasks.md atualizado corretamente
[ ] sessions.json sem inconsistências
[ ] Documentos assinados
[ ] Worktrees limpos (se aplicável)
[ ] Nenhum arquivo órfão ou conflito
[ ] Lock files removed
[ ] Branch naming correct
[ ] Merge direction correct
{
"qa_passed": true,
"score": 95,
"issues": [],
"warnings": [
"1 worktree older than 24h"
],
"recommendations": [
"Consider running /worktree prune"
]
}
| Criterion | Points | Deduction |
|---|---|---|
| All commits clean | 20 | -10 per issue |
| tasks.md correct | 15 | -15 if incorrect |
| sessions.json valid | 15 | -15 if invalid |
| Documents signed | 10 | -5 per unsigned |
| Worktrees clean | 10 | -5 per stale |
| No orphan files | 10 | -5 per orphan |
| No conflicts | 20 | -20 if conflict |
| Score | Status |
|---|---|
| 90-100 | PASSED |
| 70-89 | PASSED with warnings |
| 50-69 | CONDITIONAL (review required) |
| <50 | FAILED (must fix) |
If qa_passed == false:
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>