mozempk
154e456d4c
Confirmed via official Copilot CLI docs: there is no ask_user/elicitation tool available to custom agents (only execute/read/edit/search/agent/web/ todo aliases exist). Subagent calls made through the 'agent' tool are stateless — they run to completion and return one final result, with no mechanism to pause mid-task for a live human reply. This means conductor invoking interrogator via the agent tool could never work: interrogator would run as a subagent regardless of whether conductor itself was foreground or backgrounded, and subagents can't get real user answers. That's why it was silently writing fabricated decisions.md/ questionnaire.md content instead of actually asking anything. Fix: delete the interrogator agent entirely and fold its full Q&A procedure directly into conductor's own DESIGN PHASE, run inline in conductor's own foreground turn — never delegated. Updated the design skill/prompt, AGENTS.md, README, QUICKSTART, and role-tier config to match. Single entry point, no subagent path for anything that needs a live human answer.
722 B
722 B
name, description
| name | description |
|---|---|
| design | Use when starting gated design discovery before planning, especially when requirements are incomplete or ambiguous. |
design skill
- Invoke
.github/agents/conductor.agent.mdand run only its DESIGN PHASE section. - Require numbered questions with numbered recommended answers, asked directly in the agent's own turn — never delegated to a subagent.
- Mark one answer as recommended.
- Always include a freeform
Other:option. - Persist final answers to
.agents/specs/<slug>/decisions.md. - Stop until every required question is answered.
Do not infer decisions. Do not start planning before the user gate. Do not write an "open assumptions" section or any equivalent.