make-plan
thedotmack/claude-mem
Create detailed, phased implementation plans with documentation discovery before execution.
What is make-plan?
An orchestrator skill that creates LLM-friendly, multi-phase implementation plans by first discovering and validating actual APIs and patterns from documentation. Use when planning features, tasks, or complex implementations—especially before executing with other skills.
- Deploy subagents to discover and extract facts from documentation, examples, and code signatures
- Create phased implementation plans with explicit documentation references and verification checklists
- Frame tasks to copy proven patterns from docs rather than transform existing code
- Consolidate documentation findings into an "Allowed APIs" list with confidence notes and known gaps
- Guard against anti-patterns like invented APIs, undocumented parameters, and unverified assumptions
How to install make-plan
npx skills add https://github.com/thedotmack/claude-mem --skill make-planHow to use make-plan
- 1.Describe the feature, task, or implementation you need to plan
- 2.The skill deploys Documentation Discovery subagents to read relevant docs, examples, and signatures
- 3.Review the consolidated Phase 0 findings including Allowed APIs list and known gaps
- 4.Follow the generated phased plan, using cited documentation references for each phase
- 5.Execute each phase in separate chat contexts using the documentation references provided
- 6.Run verification checklists at phase boundaries to confirm implementations match documentation
Use cases
- Planning a multi-step feature implementation with unfamiliar APIs or frameworks
- Designing a refactor or migration by first mapping actual available methods and signatures
- Creating a task breakdown for a complex system change before delegating to execution skills
- Validating API availability and patterns across documentation before writing implementation code
- Clustering related issues into a design plan when rooted in a bug or feature backlog
- Developers planning complex features or refactors
- Teams coordinating multi-phase implementations across chat contexts
- Anyone needing to validate APIs and patterns before coding
- Project leads breaking down large tasks into executable phases
make-plan FAQ
Use make-plan when facing unfamiliar APIs, multi-step implementations, or when you need to validate what's actually available in documentation before coding. It prevents wasted effort on invented APIs or undocumented parameters.
Use oh-my-issues first if your plan is rooted in a bug or feature backlog—it clusters issues by root cause into design docs. Then use make-plan to create implementation phases from the design doc.
Each subagent must report: (1) sources consulted and what was read, (2) concrete findings with exact API names and file paths, (3) copy-ready snippet locations, and (4) confidence notes plus known gaps. Conclusions without sources are rejected.
Tasks are framed to COPY proven patterns from documentation (e.g., 'Copy the V2 session pattern from docs/examples.ts:45-60'), not to transform existing code. This ensures implementations follow documented best practices.
Phase 0 explicitly notes known gaps and confidence levels. If a subagent report lacks evidence, the orchestrator re-deploys it with targeted reads/greps before finalizing the plan.
Full instructions (SKILL.md)
Source of truth, from thedotmack/claude-mem.
name: make-plan description: Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.
Make Plan
You are an ORCHESTRATOR. Create an LLM-friendly plan in phases that can be executed consecutively in new chat contexts.
Delegation Model
Use subagents for fact gathering and extraction (docs, examples, signatures, grep results). Keep synthesis and plan authoring with the orchestrator (phase boundaries, task framing, final wording). If a subagent report is incomplete or lacks evidence, re-check with targeted reads/greps before finalizing.
Subagent Reporting Contract (MANDATORY)
Each subagent response must include:
- Sources consulted (files/URLs) and what was read
- Concrete findings (exact API names/signatures; exact file paths/locations)
- Copy-ready snippet locations (example files/sections to copy)
- "Confidence" note + known gaps (what might still be missing)
Reject and redeploy the subagent if it reports conclusions without sources.
Plan Structure
Phase 0: Documentation Discovery (ALWAYS FIRST)
Before planning implementation, deploy "Documentation Discovery" subagents to:
- Search for and read relevant documentation, examples, and existing patterns
- Identify the actual APIs, methods, and signatures available (not assumed)
- Create a brief "Allowed APIs" list citing specific documentation sources
- Note any anti-patterns to avoid (methods that DON'T exist, deprecated parameters)
The orchestrator consolidates findings into a single Phase 0 output.
Each Implementation Phase Must Include
- What to implement — Frame tasks to COPY from docs, not transform existing code
- Good: "Copy the V2 session pattern from docs/examples.ts:45-60"
- Bad: "Migrate the existing code to V2"
- Documentation references — Cite specific files/lines for patterns to follow
- Verification checklist — How to prove this phase worked (tests, grep checks)
- Anti-pattern guards — What NOT to do (invented APIs, undocumented params)
Final Phase: Verification
- Verify all implementations match documentation
- Check for anti-patterns (grep for known bad patterns)
- Run tests to confirm functionality
Key Principles
- Documentation Availability ≠ Usage: Explicitly require reading docs
- Task Framing Matters: Direct agents to docs, not just outcomes
- Verify > Assume: Require proof, not assumptions about APIs
- Session Boundaries: Each phase should be self-contained with its own doc references
Anti-Patterns to Prevent
- Inventing API methods that "should" exist
- Adding parameters not in documentation
- Skipping verification steps
- Assuming structure without checking examples
See Also
oh-my-issues— the issue-side sibling. When the plan you're being asked to make is rooted in a bug or feature backlog rather than a fresh idea, route throughoh-my-issuesfirst to cluster issues by root cause into plan masters andplans/0X-*.mddesign docs.make-planthen operates on the design doc for one plan slice.
Related skills
More from thedotmack/claude-mem and the wider catalog.
mem-search
Search persistent cross-session memory to find previous solutions and past work.
smart-explore
Token-optimized structural code search using tree-sitter AST parsing for efficient codebase exploration.
do
Execute phased implementation plans by orchestrating specialized subagents for each task.
timeline-report
Generate narrative reports analyzing a project's complete development history from claude-mem's persistent timeline.
claude-code-plugin-release
Automated semantic versioning and release workflow for Claude Code plugins with manifest sync, git tagging, and GitHub releases.
knowledge-agent
Build and query AI-powered knowledge bases from your observation history to create focused "brains" on specific topics.