claude-skills/docs/commands/cs-grill-agent-launcher.md
Claude abd9c9d8de
docs(site): generate agent-launcher pages (18th domain) + nav
generate-docs.py learns the agent-launcher domain (5 hardcoded maps extended);
regenerated docs tree: 343 skill pages / 96 agent pages / 122 command pages
(561 total). mkdocs.yml nav gains the Agent Launcher skill section (7 pages),
4 cs-agent-* agent entries, and 8 /cs:* command entries; all nav targets verified
to exist.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012FwXG6TqCXKZQvF4iD69cv
2026-08-24 17:26:12 +00:00

1.6 KiB

title description
/cs-grill-agent-launcher — Slash Command for AI Coding Agents Matt Pocock docs-anchored grill for an agent-launcher goal — walks the phase's forcing questions ONE at a time, each with a recommended answer and a. Slash command for Claude Code, Codex CLI, Gemini CLI.

/cs-grill-agent-launcher

:material-console: Slash Command :material-github: Source

Grill the current goal's phase using its SKILL.md "Forcing-question library".

$ARGUMENTS

Discipline

  • One question per turn. Never batch. Wait for the answer before the next.
  • Recommend an answer. Lead with the strongest default and why.
  • Cite the canon. Each question names its reference doc (cma-primitives.md, interview-to-config.md, loops-and-workflows.md, session-goal-model.md).
  • Refuse to advance on fuzz. If the answer is vague, restate the question with a sharper recommended option.

Question sources

Phase Forcing questions live in
interview skills/interview/SKILL.md
stage-launch skills/stage-launch/SKILL.md
grade-iterate skills/grade-iterate/SKILL.md
run-without-you skills/run-without-you/SKILL.md
wrap-up skills/wrap-up/SKILL.md
(whole plan) skills/agent-launcher-orchestrator/SKILL.md

Start with the orchestrator's five questions unless $ARGUMENTS names a phase.