
Structured Planning
Turns multi-step work into a structured, checkable plan before anyone builds it
- Repository
- EveryInc/compound-engineering-plugin
- Stars
- 25,850
- Licence
- MIT
- Files
- 15 files
What it does
Once installed, the agent stops jumping straight into doing a messy multi-step task and first writes a structured plan: what to do, in what order, how to check it, and which constraints must be kept. It works for software and non-software work, and it researches the codebase or requirements to base choices on evidence. It is designed to plan only, not to implement, so the actual building happens in a separate step.
Great for
- Developers who want an implementation plan reviewed before code is written
- Teams breaking a feature request into steps from an existing requirements doc
- People planning non-software projects who want a clear, checkable sequence
Skip it if
- Quick one-line changes, where a plan adds overhead without value
- Tasks needing an immediate answer rather than a document, since the skill can route simple work to a direct response or a chat brief
- Situations where the plan will be followed without human review on authentication, payments or migrations, because these risk surfaces are high-stakes and the skill's output still needs expert checking
Try asking
- “Plan how to add role-based access control to our admin dashboard from this requirements doc”
- “Break down the work to migrate our database to a new schema, with checks at each step”
- “Deepen the existing plan in docs/plans/billing.md with more research on edge cases”
- “Create a launch plan for our new product page with milestones and owners”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 15 original files, the MIT licence and an attribution note.
ce-plan.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip ce-plan.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip ce-plan.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Start with a requirements document or a clear feature description so the plan has solid inputs
- Say explicitly whether you want a quick chat plan or a saved plan file, since the skill picks an output format from your wording
- Review the plan before running ce-work, because the skill is designed to hand execution off rather than do it
What's inside
- references/agents/agent-native-planning-strategist.md
- references/agents/architecture-strategist.md
- references/agents/best-practices-researcher.md
- references/agents/data-integrity-guardian.md
- references/agents/framework-docs-researcher.md
- references/agents/git-history-analyzer.md
- references/agents/learnings-researcher.md
- references/agents/pattern-recognition-specialist.md
- references/agents/performance-oracle.md
- references/agents/repo-research-analyst.md
- references/agents/security-sentinel.md
- references/agents/slack-researcher.md
- references/agents/spec-flow-analyzer.md
- references/agents/web-researcher.md
- SKILL.md
Redistributed unmodified from EveryInc/compound-engineering-plugin under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.