Skip to main content
skill CX Codex

plan-writing · muaaz9329 — Claude Code skill for Cheap Agent plans

plan-writing is a Claude Code skill that drafts or repairs Cheap Agent plans before the cheapag delegate call. It activates for changes over ~20 lines, work across several files, or a rejected plan.

MIT ★ 341 updated 2026-11-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add muaaz9329/cheap-ag
/plugin install cheapag@cheap-agent
Open on GitHub

What plan-writing does

The skill writes a plan under .plan/ for Cheap Agent to carry out in an isolated repository copy. Each step names the files it can touch, the work to do, and an executable check. Steps can also declare dependencies, difficulty, and new packages.

Separate independent steps into file groups to allow parallel work; use needs: to order dependent ones. Put the original request in the shared plan context or pass it through delegate(source=…), so the worker can compare the steps with the task. List new packages in deps: because Cheap Agent cannot install them itself.

What it helps with

  • split a multi-file change into distinct steps
  • set file scope and an executable check for each step
  • order dependent work with needs:
  • repair a plan rejected by cheapag

Example prompts for the agent

  • Draft a .plan/ file for this multi-file change and give every step a check.
  • Break this change of more than 20 lines into small Cheap Agent steps.
  • Repair the plan rejected by cheapag and compare its steps with the original request.

How to install plan-writing

1Plugin marketplace

/plugin marketplace add muaaz9329/cheap-ag
/plugin install cheapag@cheap-agent

This installs the whole cheapag plugin with all its skills

2Skills CLI (Vercel)

npx skills add muaaz9329/cheap-ag --skill plan-writing -a claude-code

3Manually: put the files in place

~/.claude/skills/plan-writing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/plan-writing/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about plan-writing

How do I install plan-writing in Claude Code?

Add the marketplace with /plugin marketplace add muaaz9329/cheap-ag, then install the plugin with /plugin install cheapag@cheap-agent.

What does plan-writing do?

It creates or repairs a Cheap Agent plan with scoped steps and executable checks. It can also express dependencies between steps and group independent work for parallel execution.

What must each plan step contain?

A step needs a files: scope, a description of the work, and an executable done-when: check. Declare new packages under deps: because Cheap Agent cannot install them.

Source text

SKILL.md · MIT
---
name: plan-writing
description: Write or fix a Cheap Agent plan file before calling the cheapag delegate tool. Use when planning a change of more than ~20 lines or several files for the cheap worker, splitting work into steps, or after delegate rejects a plan.
---

# Writing a Cheap Agent plan

The cheap worker sees the whole plan, then implements the steps you name in `delegate`. It works in an isolated copy of the repo and does only what a step says, so each step must stand on its own: exact files, what to build, and a check that proves it works.

Save plans under `.plan/` in the repository, e.g. `.plan/rate-limit.md` (the developer may read, edit or commit them). Pass the path relative to the repository root.

## Grammar

```
# <plan title>                              ← required, exactly one H1
<shared context, optional, ≤ ~15 lines>
## <id> <short title>                       ← id = integer or integer+letter (3, 3a; s3, step-3 also work)
files: <path>, <dir/>, ...                  ← required; scope + overlap key
do: <what to build; continuation lines indented 2+ spaces>
done-when: <condition>; <condition>         ← required; `backticked` = executed
dont: <constraint>; <constraint>
needs: <step id>, ...
difficulty: easy | medium | hard            ← picks the worker model; wins over delegate's
kind: fix | change                          ← fix: a bug to reproduce; change: no reproduction expected
model: <model>
deps: <package@range>                       ← the step needs a new package
```

- Keys are lowercase, at the start of the line, never bullets (`- files:` is wrong). Continuation lines are indented 2+ spaces.
- In `done-when`, every `backticked` fragment is run as a shell command in the worker's copy and must exit 0. Put only commands in backticks; plain text is the worker's responsibility.
- Unknown keys (e.g. `api:`, `example:`) are passed to the worker as hints.

## Rules

- **Size:** one step ≈ under an hour of junior-developer work. Split anything bigger.
- **One change per step:** a do: that lists three or more numbered items is refused at delegate; split it into 3a, 3b, … and order them with needs:.
- **Details as bullets:** write a do: as - bullets or prose; numbered or lettered items count as separate changes, and three or more get the task refused. `do: 1. extract X 2. move Y 3. update the import` is refused; `- extract X`, `- move Y`, `- update the import` is accepted.
- **Checks:** give every step an executable `done-when` (a test command, a type check), not only prose. Name the one test file or test id the step concerns, never the whole suite.
- **Kind:** say `kind: fix` for a bug to reproduce or `kind: change` when no reproduction is expected; otherwise the worker infers it from the step's wording.
- **Source:** put the user's request or the issue verbatim in the shared context, or pass it as `delegate(source=…)` (text or a file path): the worker checks your steps against it and reports where they disagree.
- **Scope:** `files:` lists every file or directory the step may touch, accurately. It also decides which steps can run in parallel.
- **Constraints:** add `dont:` for the mistakes you expect (new dependencies, touching auth, changing public APIs).
- **Grouping:** make independent steps separate comma groups so they run in parallel; use `needs:` when one step must land first.
- **Packages:** declare a new package with `deps:`; the worker cannot install packages itself.
- Share context once at the top (conventions, existing helpers to reuse) instead of repeating it per step.

## Example

```md
# Rate limiting for auth endpoints
Redis is already wired in src/lib/redis.ts. Keep middleware style consistent with src/middleware/*.

## 1 limiter lib
files: src/lib/rateLimit.ts, test/rateLimit.test.ts
do: sliding-window limiter `limit(key, max, windowSec) -> {allowed, retryAfter}` using redis ZSET.
done-when: `npm test -- rateLimit` passes; tests cover allow, block, window expiry
dont: add dependencies

## 2 wire into login
files: src/api/login.ts, src/middleware/, test/login.test.ts
do: 5 req/min per IP on POST /api/login; on block return 429 + Retry-After.
done-when: `npm test -- login` passes; new test: 6th request → 429
dont: touch auth/session logic
needs: 1

## 3 docs
files: docs/api.md
do: document the 429 response and Retry-After.
done-when: section "Rate limits" exists under /api/login
```

## Delegating it

- `steps="3"`: one step, one job. `steps="3-5"`: a range, run in order in one job. `steps="1-2,3"`: comma-separated groups, run in parallel unless their `files:` overlap or `needs:` orders them.
- `delegate(plan=".plan/rate-limit.md", steps="1-2,3")`
- `delegate(plan=".plan/rate-limit.md", steps="2", note="use the existing ipFrom(req) helper")`: a `note` is at most 300 characters, for one-off guidance.

© muaaz9329 · MIT · muaaz9329/cheap-ag

Similar skills

All skills for Agent setup: memory, context, orchestration →

plan-writing by other authors comes first.

plan-writing davila7 plan-writing breaks work into short tasks, each with its own verification step. Useful for feature work, refactoring, or any multi-step job. CX Codex +1 188installs writing-skills Jesse Vincent Teaches agents to create, edit, and verify skills using a TDD cycle. The agent must first be caught violating a rule before writing the skill that addresses it. CX Codex +1 217,894installs technical-writing riekelt technical-writing — a skill for drafting and reviewing technical documents with source and style rules. Use it for READMEs, specs, design docs, reports, and plans. CX Codex +1 27,800installs writing-runbooks riekelt A skill for writing runbooks, setup and release procedures, migration guides and troubleshooting entries people execute under time pressure. CX Codex +1 26,700installs changelog-writing Samuel Berthe changelog-writing turns raw commits, pull requests and tickets into release notes people actually read: what shipped, what it means, what breaks. CX Codex +1 13,400installs om-spec-writing open-mercato The om-spec-writing skill drafts and reviews feature specifications, moving from a minimal skeleton and open questions to architecture notes and an implementation plan. CX Codex +1 3,900installs jupyter-notebook-writing zc277584121 jupyter-notebook-writing — a skill for editing Jupyter notebooks in Markdown instead of JSON. Runs on Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode; edit .md files first, then convert to .ipynb using jupyter-switch. CX Codex +1 3,900installs

From the same set8

Project sponsors

Companies that keep this analytics open