make-plan

A planning command that turns product requirements into a structured implementation plan linking features to code areas and assigned work phases.

In plain words
What is it for?
Use it to create plan documents from requirements and architecture notes, organize implementation tasks, and assign them to agents.
Why use it?
It helps connect what a product should do with the code changes needed, so work can be divided and traced back to requirements.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/context4ai/workflow/make-plan
Any agent
npx skills add context4ai/workflow --skill make-plan
Clone the repo
git clone --depth 1 https://github.com/context4ai/workflow

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.04547
Opus 5 $0.00021 $0.02273
Sonnet 5 $0.00008 $0.00909
Haiku 4.5 $0.00004 $0.00455

Measured yesterday against content hash cbb6603d0d99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/make-plan/SKILL.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/make-plan - Implementation Plan Modeling (Code-Layer Graph)

Based on the PRD (Product-layer graph), model the implementation plan as a Code-layer Node / Edge / Fact graph.

Design Workspace (design-dir)

The default workspace for design documents is design/. When the Agent starts, it checks:

  1. design/ directory exists -> use design/ as <design-dir>
  2. design/ does not exist -> pause and ask the user for the design workspace path, explaining the accepted organizational structure:
    <design-dir>/<version>/(prd|plan).md
    Examples: design/v1.0.1/prd.md, design/v0.5.0/plan.md
    

design/archive/: Archived or inactive design documents. When exploring existing graph structures, treat as low-priority reference -- prioritize reading active version directories, and only fall back to archive when relevant context cannot be found in active versions.

All subsequent paths using <design-dir> refer to this directory.


TL;DR -- First-Screen Hard Rules

  • Input: PRD + core architecture docs (required)
  • Output: Package/Symbol Node tree + Edges + Facts (organized by Phase), written to <design-dir>/<version>/plan.md
  • Prohibited: Do not produce Product Nodes (that belongs to PRD); example code <=10 lines
  • Minimum output: Every [new]/[modified] Node >= 1 [guide] + >= 1 [spec] (leaf nodes may reuse parent's)
  • Spec numbering: Plan uses [P1] [P2] ...; implements uses -> implements: PRD[S3]
  • Coverage requirement: Every PRD [Sn] spec must be implemented by at least 1 Plan spec
  • Internal must be listed too: Plan is a change manifest not a repository snapshot; internal Symbols are marked visibility=internal
  • corresponds should target Symbol-level, do not coarsely connect to Package
  • Fact changes: Modifying old Facts requires [-kind] + [+kind] + supersedes association
  • content <= 256 chars, detail is optional inline (> block); over 100 lines link to details/
  • Code exploration must use tools (Glob/Grep/Read); never fabricate file paths

Read the full file on GitHub · 466 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 466 lines · 42 tokens per session scan A cbb6603d0d99

Subscribe to this mod's changes

make-plan is a skill published in the GitHub repository context4ai/workflow (4 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 4,547 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens