plan

An interactive feature-planning workflow that creates documents for why a feature matters, what it should do, how it should work, and the order of delivery.

In plain words
What is it for?
Use it to research and plan an existing feature, create product and design documents, break work into steps, or create GitHub sub-issues.
Why use it?
It gives feature work a structured discovery process and keeps plans in story folders instead of scattered planning files.

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/abilenduke/copilot-developer/plan
Any agent
npx skills add ABilenduke/copilot-developer --skill plan
Clone the repo
git clone --depth 1 https://github.com/ABilenduke/copilot-developer

Made for: Claude Code, Codex.

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,140 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 $0.00111 $0.05140
Opus 5 $0.00056 $0.02570
Sonnet 5 $0.00022 $0.01028
Haiku 4.5 $0.00011 $0.00514

Measured yesterday against content hash edc7396f3f8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/plan/SKILL.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Planner Skill

⛔ HARD RULES — READ BEFORE DOING ANYTHING

These rules are absolute. No exceptions. No workarounds.

Rule 1: NEVER create features

You do NOT create feature directories, feature READMEs, or update the feature index. EVER.

If the user names a feature that does not exist under docs/features/, STOP and tell them: "The feature '{name}' doesn't exist in the catalog. Please run /feature to create it first, then come back to /plan."

Feature creation belongs to /feature. Not you. Not ever.

Rule 2: ALWAYS use the story directory structure

Plans go here and ONLY here:

docs/features/{feature}/stories/{YYYY-MM-DD}_{story-name}/plan.md

CORRECT:

docs/features/auth/stories/2026-02-21_add-oauth2/plan.md

WRONG — all of these are WRONG:

docs/features/auth/plan.md
docs/features/auth/stories/plan.md
docs/plans/auth-add-oauth2.md

Format detection: If the user points you at an existing directory under iterations/, use the old monolithic format (backward compatibility). If creating new work, always use stories/.

Rule 3: NEVER skip the done gate

Each document layer has a done gate. Do not write the file until the gate criteria are met through the interactive process.

Verification Checklist (run before Phase 1)

  • docs/features/ exists? If no → STOP, tell user to run /feature
  • Target feature directory exists? If no → STOP, tell user to run /feature
  • Story directory exists or can be created at docs/features/{feature}/stories/{YYYY-MM-DD}_{story-name}/?
  • All checks pass? → Proceed

Purpose

This skill enforces a planning-first discipline for software development. Before any code is written, you walk the developer through an interactive 7-phase discovery process that produces four altitude-layered documents:

Document Question Phase(s) Mutable?
brief.md WHY are we doing this? Phase 1 Immutable after approval
prd.md WHAT are we building? Phases 2 + 6 Immutable after approval
design.md HOW will we build it? Phases 3-5 Immutable after approval
plan.md WHEN and in what ORDER? Phase 7 Immutable after approval

Read the full file on GitHub · 544 lines

Files

What ships with it

6 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 · 544 lines · 111 tokens per session scan A edc7396f3f8a

Subscribe to this mod's changes

plan is a skill published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 111 tokens to every session and 5,140 once invoked, about $0.0006 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