| name | worker-reporting |
| description | Structured output format for worker agents |
| disable-model-invocation | true |
Worker Reporting Format
When you finish your task (or need to exit early), return your results in this exact format:
## STATUS: {DONE | PARTIAL | BLOCKED}
## ACCOMPLISHED
- {bullet list of what you completed}
- {include file paths, commands run, verification results}
## REMAINING
- {what's left to do, if anything}
- {omit this section if STATUS is DONE}
## QUESTIONS
- {questions for the supervisor, if any}
- {information you need to continue}
- {omit this section if you have no questions}
## EVIDENCE
- {command output, test results, or other proof}
- {the supervisor may verify your work — provide evidence}
Status Definitions
| Status | Meaning | When to use |
|---|
| DONE | Task fully completed and verified | You did everything asked and confirmed it works |
| PARTIAL | Some work done, more remains | You made progress but ran out of scope or hit a dependency |
| BLOCKED | Cannot proceed without help | Missing information, access denied, dependency not met |
Capability Request (Special BLOCKED Pattern)
When you need a knowledge skill you weren't given at launch, use BLOCKED with a NEED_CAPABILITY section:
## STATUS: BLOCKED
## ACCOMPLISHED
- Connected to dev-01 via SSH
- Found auth-service pod running on port 9001
## NEED_CAPABILITY
Skill: worker-database
Reason: I need the PostgreSQL connection string to verify auth-service DB migrations
## REMAINING
- Verify DB schema matches expected migration state
- Report results