/plan
Called by team.md router when action is `plan`.
$ npx -y skills add coco-research/coco --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/plan
Context preview
What this command does when you run it.
Called by team.md router when action is `plan`.
Command definition
plan.md/team plan — Planning Pipeline
> Called by team.md router when action is `plan`.
Role Selection Bias
| Layer | Preferred Roles | Count | |-------|----------------|-------| | L1 | technical-analyst, business-analyst, domain-researcher | 2-3 | | L2 | senior-pm, (domain-dependent engineers), jira-specialist (if Jira workflow planning) | 2-3 | | L3 | domain-accuracy, doc-quality | 2 | | L4 | principal-pm | 1 |
Pipeline Customization
Layer 1: Scope Research
L1 agents assess:
- Current state of the system/project. When `.arch/index.json` exists and is CURRENT, read
`.arch/INDEX.md` for the component map instead of re-deriving the structure — it is a validated artifact in which every path has been confirmed to exist.
- What's already been built vs what's needed
- Dependencies and sequencing constraints
- Risk areas that need mitigation in the plan
Layer 2: Plan Creation
- **Mode:** `default` (creates plan documents, not source code)
- Agents produce structured plans with:
- Phase breakdown with clear goals
- Task decomposition within each phase
- Dependency graph (what blocks what)
- Effort estimates and sequencing
- Success criteria per phase
**Toolkit integration:**
- Check team:toolkit.md for "Project Orchestration" entry
- If GSD active → create PLAN.md files compatible with GSD format (frontmatter: wave, depends_on, files_modified, autonomous, requirements, must_haves). When `.arch/index.json` exists and is CURRENT, populate `files_modified` from the primary paths of the components the phase touches, then narrow it to the actual files — component paths are the starting set, never the final answer, because a component may own thousands of files.
- If no GSD → create standalone plan documents
GSD Integration (C4)
When `.planning/` exists:
- Read ROADMAP.md and REQUIREMENTS.md for context
- Plans follow GSD conventions
- Output: `.planning/phases/{phase_dir}/PLAN.md` files with proper frontmatter
- Compatible with `/gsd:execute-phase`
Layer 3: Plan Validation
L3 agents check:
- Are all requirements covered?
- Is the task decomposition achievable?
- Are dependencies correctly mapped?
- Are estimates realistic?
- Are success criteria measurable?
Layer 4: Plan Approval
Principal reviews for:
- Strategic alignment
- Resource efficiency
- Risk coverage
- Sequencing optimality
Read more
/team plan — Planning Pipeline
> Called by team.md router when action is `plan`.
Role Selection Bias
| Layer | Preferred Roles | Count | |-------|----------------|-------| | L1 | technical-analyst, business-analyst, domain-researcher | 2-3 | | L2 | senior-pm, (domain-dependent engineers), jira-specialist (if Jira workflow planning) | 2-3 | | L3 | domain-accuracy, doc-quality | 2 | | L4 | principal-pm | 1 |
Pipeline Customization
Layer 1: Scope Research
L1 agents assess:
- Current state of the system/project. When `.arch/index.json` exists and is CURRENT, read
`.arch/INDEX.md` for the component map instead of re-deriving the structure — it is a validated artifact in which every path has been confirmed to exist.
- What's already been built vs what's needed
- Dependencies and sequencing constraints
- Risk areas that need mitigation in the plan
Layer 2: Plan Creation
- **Mode:** `default` (creates plan documents, not source code)
- Agents produce structured plans with:
- Phase breakdown with clear goals
- Task decomposition within each phase
- Dependency graph (what blocks what)
- Effort estimates and sequencing
- Success criteria per phase
**Toolkit integration:**
- Check team:toolkit.md for "Project Orchestration" entry
- If GSD active → create PLAN.md files compatible with GSD format (frontmatter: wave, depends_on, files_modified, autonomous, requirements, must_haves). When `.arch/index.json` exists and is CURRENT, populate `files_modified` from the primary paths of the components the phase touches, then narrow it to the actual files — component paths are the starting set, never the final answer, because a component may own thousands of files.
- If no GSD → create standalone plan documents
GSD Integration (C4)
When `.planning/` exists:
- Read ROADMAP.md and REQUIREMENTS.md for context
- Plans follow GSD conventions
- Output: `.planning/phases/{phase_dir}/PLAN.md` files with proper frontmatter
- Compatible with `/gsd:execute-phase`
Layer 3: Plan Validation
L3 agents check:
- Are all requirements covered?
- Is the task decomposition achievable?
- Are dependencies correctly mapped?
- Are estimates realistic?
- Are success criteria measurable?
Layer 4: Plan Approval
Principal reviews for:
- Strategic alignment
- Resource efficiency
- Risk coverage
- Sequencing optimality
Meet Coco. A superintelligent agent framework powered by an advisory board of 389 world-class minds. Scale your AI assistant into a complete engineering department with 142 skills, 277 commands, and persistent state. Universal compatibility. Local privacy. Free and open source.
Repo: coco-research/coco
Other commands on coco.
- /mermaid
Build beautiful Mermaid diagrams using beautiful-mermaid. Covers all 6 diagram types, theming, SVG/ASCII output, and CoCo Platform integration.
Open command - /read
Show latest emails from a specific person. Usage: /email-read alice
Open command - /reply
Draft a reply to a specific email. Usage: /email-reply Project Phase 2 Contract Data
Open command - /save
Save matching emails to a project folder for sync processing. Usage: /email-save alice to emails/
Open command - /search
Search emails by subject keywords. Usage: /email-search github webhook
Open command - /summary
AI summary of today's emails — key decisions, action items, meetings. No arguments needed.
Open command

