一键导入
plan
Use when starting any non-trivial task - classifies task level (L0-L3), runs appropriate planning agents, produces intent document and execution plan
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when starting any non-trivial task - classifies task level (L0-L3), runs appropriate planning agents, produces intent document and execution plan
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Use after implementation to run independent code review - dispatches reviewer agents based on task level, ensures author-reviewer separation
Use for the L2+ browser-QA gate. Real-browser mode (Playwright Chromium) is opt-in (--browse / SGC_QA_REAL=1); by default runs a stub returning concern (never rubber-stamps). Writes verdict + findings to reviews/{task}/qa/.
Use when starting any conversation - establishes SGC commands, routes tasks to appropriate skills, and enforces system invariants
Use to capture knowledge from solved problems - extracts structured solution documents via 4 specialized agents with dedup enforcement
Use when requirements are unclear, before planning - clarifies goals, constraints, and acceptance criteria through structured questioning
Use when ready to release - verifies all evidence, runs ship gate, handles deployment, triggers compound janitor
| name | plan |
| description | Use when starting any non-trivial task - classifies task level (L0-L3), runs appropriate planning agents, produces intent document and execution plan |
Classify the task, dispatch planning agents, produce an immutable intent + feature list.
Core principle: every plan step names concrete files and changes — no placeholders.
/plan <task>/discover confirms requirements| Directory | Access |
|---|---|
| decisions | R+W |
| progress | RW |
| solutions | R |
| reviews | R |
This skill invokes the dispatcher; process is authoritative in code, not prose.
src/commands/plan.ts (runPlan)src/dispatcher/agents/classifier-level.tsplanner.eng (L1+), +planner.ceo +researcher.history (L2+), +planner.adversarial (L3)contracts/sgc-capabilities.yaml--signed-by + interactive yes · §11 classifier rationale specificplugins/sgc/CLAUDE.mdWhen this skill is invoked, dispatch to the sgc CLI:
bun src/sgc.ts plan "$ARGUMENTS"
For L3 tasks, the CLI will prompt for --signed-by and require interactive yes.
To override auto-classified level: --level L0|L1|L2|L3 (upgrade-only).
sgc plan produces intent.md + feature-list.md. For deep implementation planning:
sp:writing-plans — task-by-task execution plansp:brainstorming — clarify ambiguous scope before planningsgc owns classification + intent; sp owns the deep plan body.