| name | gate-judgment |
| description | Evaluate a candidate against gate criteria and render GO/KILL/RECYCLE verdict with evidence. |
| execution | subagent |
| prompt | ./prompt.md |
| input | candidate, gate_criteria |
| dependencies | {"sops":["spawn-agent"]} |
Gate Judgment
Evaluate a specific candidate against defined gate criteria and render a verdict: GO (proceed to next stage), KILL (terminate), or RECYCLE (rework and re-evaluate). Every verdict is backed by evidence.
Execution
Spawns a subagent that:
- Receives candidate data and gate criteria specification
- Evaluates candidate against each criterion
- Applies the pass rule to determine overall verdict
- Documents evidence for each criterion evaluation
- Specifies conditions for advancement if verdict is not GO
Why Subagent
Gate judgment must be rigorous and unbiased. A dedicated subagent applies criteria mechanically without emotional attachment to the candidate, ensuring honest evaluation.
HARD-GATE
Output MUST include: verdict (GO/KILL/RECYCLE), per-criterion evaluation with evidence, and conditions for advancement. Reject if verdict is not supported by criterion-level evaluation.
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
