Skip to content

Make Plan

Turns a feature or task into a phased, verifiable implementation plan for the agent to follow.

Stars
110,174
Licence
Apache-2.0
Files
1 file

What it does

When installed, the agent stops jumping straight into code for multi-step work. It first gathers facts from docs and existing examples (often via sub-agents), writes a phased plan where each phase cites specific sources and includes verification checks, and then presents a short summary in a fixed format. It is written for handing work across fresh chat sessions, so each phase is meant to stand on its own.

Great for

  • Developers planning a multi-step feature before letting an agent write code
  • Teams who want plans grounded in cited documentation rather than assumed APIs
  • People using the agent for work that will span several separate chat sessions

Skip it if

  • Simple one-line fixes or quick questions, since the process adds heavy overhead
  • Non-developers without a codebase or API docs to reference, because the plan relies on citing them
  • Anyone expecting the skill to execute the plan itself; it only produces the plan document

Try asking

  • “Plan a feature for adding user login with OAuth before we start coding”
  • “Make a phased plan to migrate our session handling to the new API, with docs references”
  • “Create an implementation plan for the export feature that I can run in separate chat sessions”
Step-by-step guide: how to use Make PlanInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    make-plan.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip make-plan.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip make-plan.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 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

  • Point the agent at your real documentation or repo folders so the discovery phase has sources to cite.
  • Review the generated plan file before approving execution, especially the Phase 0 API list.
  • Use it before the do skill, which the description names as the execution step.

What's inside

  • SKILL.md

Redistributed unmodified from thedotmack/claude-mem under the Apache-2.0 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.