How do I install the Code Plan skill?

Run npx skillmds@latest add alexeyshishin/code-plan in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Plan safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Plan?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Plan free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Plan?

alexeyshishin (@alexeyshishin) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Plan by alexeyshishin — Agent Skill

Name: Code Plan
Author: alexeyshishin

Code Plan

Design a feature before writing code. Spawns planner + skeptic subagents that read the Memory Bank, argue, and write a plan to swarm-report/. Use BEFORE /code-build, for any feature touching 2+ files or with unclear scope. Skip for typos and one-line fixes.

alexeyshishin d5b44ef 2 files · 3.6 KB Updated Sep 17, 2026

File contents

Skill: /code-plan

You are the ORCHESTRATOR. You do not design the plan yourself — you run two subagents and merge their output. No code edits here.

Invocation

/code-plan "<one-sentence feature>"

Steps

Slugify the feature → <slug> (kebab-case, short).
Read context yourself (cheap, keeps subagents focused): .memory-bank/index.md if it exists. If it does not, tell the user: "No Memory Bank found — plan will rest only on your description." and continue.
Spawn 2 subagents in parallel — one message, two Task calls, subagent_type: general-purpose. Prefix EACH prompt with:

Answer TERSE: terse, drop filler, keep all technical substance.
- planner — "Read .claude/agents/planner.md and follow it exactly. Feature: ."
- skeptic — "Read .claude/agents/skeptic.md and follow it exactly. Feature: ."
(Sharper, slightly pricier variant: run planner first, then pass its YAML into the skeptic prompt so it critiques the concrete plan. One extra round-trip. Use it when the feature is risky.)
Merge (orchestrator only): take the planner's plan, apply the skeptic's HIGH/MED fixes, and list anything unresolved under Blockers.

Write swarm-report/<slug>-plan.md:

# Plan: <feature>   (slug: <slug>)
## TL;DR
## Acceptance criteria  — observable "done" conditions; /code-review checks these
## Plan                 — merged steps + affected files + tests
## Blockers             — skeptic HIGH not yet resolved (human decides)
## Out of scope
## Assumptions

Report to user: TL;DR + any Blockers. If Blockers exist, ask the user to resolve them before /code-build.

---name: code-plandescription: Design a feature before writing code. Spawns planner + skeptic subagents that read the Memory Bank, argue, and write a plan to swarm-report/. Use BEFORE /code-build, for any feature touching 2+ files or with unclear scope. Skip for typos and one-line fixes.---# Skill: /code-planYou are the ORCHESTRATOR. You do not design the plan yourself — you run two subagentsand merge their output. No code edits here.## Invocation`/code-plan "<one-sentence feature>"`## Steps1. **Slugify** the feature → `<slug>` (kebab-case, short).2. **Read context yourself** (cheap, keeps subagents focused): `.memory-bank/index.md` if it exists. If it does not, tell the user: "No Memory Bank found — plan will rest only on your description." and continue.3. **Spawn 2 subagents in parallel** — one message, two `Task` calls, `subagent_type: general-purpose`. Prefix EACH prompt with: > Answer TERSE: terse, drop filler, keep all technical substance. - **planner** — "Read `.claude/agents/planner.md` and follow it exactly. Feature: <verbatim>." - **skeptic** — "Read `.claude/agents/skeptic.md` and follow it exactly. Feature: <verbatim>." (Sharper, slightly pricier variant: run planner first, then pass its YAML into the skeptic prompt so it critiques the concrete plan. One extra round-trip. Use it when the feature is risky.)4. **Merge** (orchestrator only): take the planner's plan, apply the skeptic's HIGH/MED fixes, and list anything unresolved under **Blockers**.5. **Write** `swarm-report/<slug>-plan.md`: ``` # Plan: <feature> (slug: <slug>) ## TL;DR ## Acceptance criteria — observable "done" conditions; /code-review checks these ## Plan — merged steps + affected files + tests ## Blockers — skeptic HIGH not yet resolved (human decides) ## Out of scope ## Assumptions ```6. **Report to user**: TL;DR + any Blockers. If Blockers exist, ask the user to resolve them before `/code-build`.

Frequently asked questions