pm-plan

pm-plan is a skill for Claude Code, Codex from Hank95/mdpm. It costs 15 tokens per session (758 once invoked), scanned A, original, MIT.

A feature-planning command that breaks a large feature or epic into three to eight smaller tasks. It records which tasks depend on others and defines how each task is considered complete.

In plain words
What is it for?
Use it to plan a new feature or split an existing task into subtasks, using the repository roadmap and architecture decisions as context.
Why use it?
It turns a broad request into work that can be tackled, tested, and reviewed in manageable pieces. It also makes the required order of work clearer.

Skill for Claude CodeCodex

Part of the mdpm plugin — 17 skills shipped together

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/hank95/mdpm/pm-plan
Any agent
npx skills add Hank95/mdpm --skill pm-plan
Clone the repo
git clone --depth 1 https://github.com/Hank95/mdpm

Made for: Claude Code, Codex.

Or install mdpm, the plugin that ships this one along with the rest of its 17 skills.

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.

agentmods badge for pm-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/hank95/mdpm/pm-plan.svg)](https://agentmods.dev/skills/hank95/mdpm/pm-plan)
Your own site
<a href="https://agentmods.dev/skills/hank95/mdpm/pm-plan"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 758 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 $0.00015 $0.00758
Opus 5 $0.00008 $0.00379
Sonnet 5 $0.00003 $0.00152
Haiku 4.5 $0.00002 $0.00076

Measured 4d ago against content hash 146ccea3d10d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-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 4d 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.

skills/pm-plan/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pm-plan

Decompose a feature into a set of tasks with proper sequencing.

Argument $ARGUMENTS is either:

  • A freeform feature description ("add user authentication with magic links")
  • An existing task ID (like PRJ-042) to decompose into subtasks

Steps

  1. Load context.

    • Read docs/ROADMAP.md to understand the current milestone.
    • Read docs/DECISIONS.md — existing architecture constraints matter.
    • If $ARGUMENTS is a task ID, read that task file for objective/notes/AC.
  2. Ask clarifying questions only if truly needed. The user is busy. Make reasonable assumptions from the codebase and stated description. Ask at most 1-2 focused questions, not a survey.

  3. Decompose into 3-8 tasks. Each task must:

    • Be completable in a bounded chunk (hours to a couple of days, not weeks).
    • Have a clear "done" condition — visible in acceptance criteria.
    • Be independently testable/demonstrable where possible.
    • Have explicit depends_on if it requires another task in the set to be finished first.
  4. Present the plan to the user for review BEFORE creating files:

    ## Plan: <feature name>
    
    1. [NEW] Task A — 1-line description (priority: high)
    2. [NEW] Task B — 1-line description (priority: high, depends on: A)
    3. [NEW] Task C — 1-line description (priority: medium, depends on: A)
    4. [NEW] Task D — 1-line description (priority: medium, depends on: B, C)
    ...
    
    Dependencies: A → B, A → C, {B,C} → D
    Estimated sequence: A, then B+C in parallel, then D.
    
  5. Get confirmation. Ask: "Create these as backlog tasks?" Let the user edit the plan before writing files. They may want to split/merge tasks, adjust priorities, or drop items.

  6. Create the task files once confirmed. For each task:

    • Generate a unique ID using the same rules as /pm-new (scan all existing IDs, pick max + 1).
    • Use the template from /pm-new, including the <ID>-<slug>.md filename convention.
    • Populate depends_on with the correct IDs of sibling tasks.
    • Set tags consistently across the set (often a shared feature name).
    • Write to tasks/backlog/.

Read the full file on GitHub · 65 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. 4d ago First seen · 65 lines · 15 tokens per session scan A 146ccea3d10d

Subscribe to this mod's changes

pm-plan is a skill published in the GitHub repository Hank95/mdpm (3 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 758 once invoked, about $0.0001 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

sideboard

Maintain and display a live project roadmap/kanban board backed by GitHub Issues. Use when the user asks to see, set up, or update the roadmap, add a feature to build next, mark an item in-progress or done, or when a chat naturally decides on upcoming work worth tracking. Manages the roadmap via gh (GitHub Issues) and…

mmyslin/sideboard · 86 tokens

project-manager

This skill has been upgraded with agentic AI capabilities, OKR/KPI integration patterns, and async-first workflows based on 2026 PM best practices research.

buiphucminhtam/forgewright · 68 tokens

kanban-md

Manage project tasks using kanban-md, a file-based kanban board CLI. Use when the user mentions tasks, kanban, board, backlog, sprint, project management, work items, priorities, blockers, or wants to track, create, list, move, edit, or delete tasks. Also use for standup, status update, sprint planning, triage, or…

antopolskiy/kanban-md · 82 tokens

kanban-based-development

Autonomous, parallel-safe development workflow using kanban-md. Use when the user asks to work through tasks, do kanban-based development, or when multiple agents need to coordinate work on the same codebase. Optimized for explicit handoffs and a "defer to user" protocol when human intervention is required.

antopolskiy/kanban-md · 68 tokens

alive:create-walnut

Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.

alivecontext/alive · 63 tokens

alive:bundle

Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.

alivecontext/alive · 34 tokens