create-plan

A method for writing detailed implementation plans before changing a codebase, including tasks, checks, risks, and alternative approaches.

In plain words
What is it for?
Use it when you need a validated Markdown plan for a feature, architectural change, or other multi-step implementation.
Why use it?
It reduces missed dependencies and unclear decisions on complex work by requiring the project structure and relevant code paths to be examined first.

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/justrach/codegraff2/create-plan
Any agent
npx skills add justrach/codegraff2 --skill create-plan
Clone the repo
git clone --depth 1 https://github.com/justrach/codegraff2

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 910 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00095 $0.00910
Opus 5 $0.00048 $0.00455
Sonnet 5 $0.00019 $0.00182
Haiku 4.5 $0.00010 $0.00091

Measured yesterday against content hash 6e8e8efd55ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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.

The scan reads SKILL.md. This mod also ships 2 executable files (validate-all-plans.sh, validate-plan.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to create-plan — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.forge/skills/create-plan/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Implementation Plan

Generate comprehensive implementation plans that provide strategic guidance without making actual code changes.

When to Use

  • User explicitly requests a plan, roadmap, or implementation strategy
  • Complex tasks requiring structured breakdown before implementation
  • Need for risk assessment and alternative approach analysis
  • Pre-implementation analysis of architectural decisions

Planning Process

1. Initial Assessment

Research the codebase to understand:

  • Project structure and organization
  • Relevant files and components - read thoroughly to understand complete flows
  • Existing patterns and conventions
  • Potential challenges and risks
  • Data flows from entry points to final usage

Use search, sem_search, and read tools to examine the codebase. Use sage if deeper research is required for the use-case. Explicitly cite sources using filepath:line format in your plan.

2. Create Strategic Plan

Generate a Markdown plan file in plans/ directory with naming: plans/{YYYY-MM-DD}-{task-name}-v{N}.md

Example: plans/2025-11-24-add-auth-v1.md

3. Validate Plan

MANDATORY: Run the validation script to ensure the plan meets all requirements:

./.forge/skills/create-plan/validate-plan.sh plans/{YYYY-MM-DD}-{task-name}-v{N}.md

Fix any errors or warnings and re-validate until the plan passes all checks.

4. Plan Structure

# [Task Name]

## Objective

[Clear statement of goal and expected outcomes]

## Implementation Plan

- [ ] 1. [First task with detailed description and rationale]
- [ ] 2. [Second task with detailed description and rationale]
- [ ] 3. [Third task with detailed description and rationale]

## Verification Criteria

- [Criterion 1: Specific, measurable outcome]
- [Criterion 2: Specific, measurable outcome]

## Potential Risks and Mitigations

1. **[Risk Description]**
   Mitigation: [Specific mitigation strategy]

2. **[Risk Description]**
   Mitigation: [Specific mitigation strategy]

## Alternative Approaches

1. [Alternative 1]: [Brief description and trade-offs]
2. [Alternative 2]: [Brief description and trade-offs]

Read the full file on GitHub · 117 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 117 lines · 95 tokens per session scan A 6e8e8efd55ac

Subscribe to this mod's changes

create-plan is a skill published in the GitHub repository justrach/codegraff2 (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 95 tokens to every session and 910 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to create-plan, differing in 0 lines, and is treated as a copy.

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