What is project.create_plan?

A planning workflow that turns product requirements and design documents into an ordered implementation plan made of versions and pull requests.

Use it to create or extend a project plan, define component specifications, and describe the next pull requests in detail.

It gives a project a dependency-aware sequence of work before coding begins and asks for clarification when the design is unclear.

project.create_plan — Skill for Claude Code by gpsaggese/helpers

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.

Any agent

npx skills add gpsaggese/helpers --skill project.create_plan

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/project.create_plan/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/project.create_plan)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/project.create_plan"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/project.create_plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gpsaggese/helpers/project.create_plan"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/project.create_plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 811 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00811
Opus 5.5	$0.00005	$0.00324
Sonnet 5.5	$0.00003	$0.00162
Haiku 4.5	$0.00001	$0.00081

Measured yesterday against content hash a79a3191b9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project.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.

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.

.claude/skills/project.create_plan/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given the PRD and design docs, write docs/04-plan.md: what to build, in which order, as versions and PRs
Do not implement code and do not create GitHub issues

Input

<DESIGN>: the design overview, e.g., docs/02-design.architecture.md
<DOCS_DIR>: the docs/ dir of the project, optional
- If missing, use the dir of <DESIGN>

Workflow

Read the Inputs

Read <DESIGN>, the other 02*-design.*.md files, and <DOCS_DIR>/01-prd.md
If <DOCS_DIR>/04-plan.md exists, extend it instead of replacing it

Ask If the Design Is Unclear

If the scope or the order of the work is not perfectly clear:
- Do not write the plan
- Ask the user for clarification
- Wait for the answers

Split Into Versions

Split the work into versions. Each version must run and be demoable
Order versions so that each needs only the versions before it
Put components and their open questions in "Component Specs"

Write the PR Entries

Write the PR entries of the next version in detail
Keep later versions as a few bullets
Name PRs PR_<component letter><number>. Never reuse an id, per .claude/skills/project.rules.md section "Name the PRs"
Mark each PR that needs a spec. It gets one later with .claude/skills/auto_task.create_plan_for_feature/SKILL.md
Order PRs by dependency first, then by increasing complexity

Write the Plan File

Create <DOCS_DIR>/04-plan.md
Follow .claude/skills/project.rules.md section "Plan File"
Follow the template .claude/templates/project_plan.template.md
Follow .claude/skills/markdown.rules.md and .claude/skills/text.rules.md when writing text
Add the execution part only if the user says several people work in parallel
If <DOCS_DIR>/07-progress.md does not exist, create it from .claude/templates/project_progress.template.md

Update the Index

Add a row for each new doc to <DOCS_DIR>/README.md, if the file exists

Conventions

Follow .claude/skills/project.rules.md for project docs
Follow .claude/skills/markdown.rules.md and .claude/skills/text.rules.md
Say in each file you create how it was generated, with this line right after the title:
```
- Generated by `.claude/skills/project.create_plan/SKILL.md`
```

Read the full file on GitHub · 92 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.

yesterday First seen · 92 lines · 13 tokens per session scan A a79a3191b9a7

Subscribe to this mod's changes

project.create_plan is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 811 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-06.

Planning Project management

project.create_plan next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
project.create_plangpsaggese/helpers	Skill	158	today	Apache-2.0	A	13	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex