project-plan

A planner for large software projects that span multiple coding-agent sessions. It breaks the work into ordered sessions, tracks progress in a project plan file, and uses approval points.

In plain words
What is it for?
Use it to turn requirements into a staged plan, execute one session at a time, record changes, and continue unfinished work later.
Why use it?
It prevents long projects from losing their scope, current status, or completed work between sessions.

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/abilityai/abilities/plan
Any agent
npx skills add Abilityai/abilities --skill plan
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,431 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 $0.00032 $0.02431
Opus 5 $0.00016 $0.01215
Sonnet 5 $0.00006 $0.00486
Haiku 4.5 $0.00003 $0.00243

Measured 2d ago against content hash d3dcfb4946e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 2d ago.

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.

plugins/agent-dev/skills/plan/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Planner

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. project-plan vX.Y — recent: <summary>. Then proceed.

Purpose

Manage large projects that span multiple Claude sessions. On first run, analyze the project scope and produce a session-by-session execution plan. On subsequent runs, execute the next session and update state until the project is complete.

State Dependencies

Source Location Read Write Description
Project plan project_plan.yaml Y Y Session plan, status, and history
Project inputs User-provided files/description Y Raw project requirements
Workspace files Varies per project Y Y Files modified during sessions

Inputs

  • $0: Project name (used as prefix for project_plan.yaml, e.g., refactorrefactor_project_plan.yaml)
  • $1: (Optional) Path to input file(s) with project requirements, OR verbal description

Process

Step 0: Detect Mode

Check if project_plan.yaml (or [name]_project_plan.yaml) exists and has incomplete sessions:

  • No plan exists OR all sessions completed → Go to Phase A: Plan
  • Plan exists with incomplete sessions → Go to Phase B: Execute

Parse any flags:

  • --status → Show progress summary, then stop
  • --plan <input> → Force new plan creation (Phase A)
  • --session N → Jump to session N in Phase B
  • --skip N → Mark session N as skipped
  • --abandon → Mark project as abandoned
  • --add "change" → Append a change to the backlog

Phase A: Plan a New Project

A1: Gather Project Scope

Read all input materials:

  • If input file(s) provided: read them fully
  • If verbal description: capture from conversation
  • Ask clarifying questions if scope is ambiguous

Identify:

  • What changes: List every file, component, or system that needs modification
  • What the changes are: For each item, what specifically needs to happen
  • Dependencies: Which changes depend on others being done first

Read the full file on GitHub · 329 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. 2d ago First seen · 329 lines · 32 tokens per session scan A d3dcfb4946e9

Subscribe to this mod's changes

project-plan is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 32 tokens to every session and 2,431 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 2026-08-30.

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