pm-start

pm-start is a skill for Claude Code, Codex from Hank95/mdpm. It costs 10 tokens per session (509 once invoked), scanned A, original, MIT.

A command that moves a project task from the backlog into active work. The backlog is the list of planned tasks that have not started yet.

In plain words
What is it for?
Use it to begin a task by ID or title, handle dependency warnings, and inspect the work log when a task is already active.
Why use it?
It starts work through the project manager while checking dependencies and preserving the task's history. It also explains problems such as missing or ambiguous task references.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

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-start
Any agent
npx skills add Hank95/mdpm --skill pm-start
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-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/hank95/mdpm/pm-start.svg)](https://agentmods.dev/skills/hank95/mdpm/pm-start)
Your own site
<a href="https://agentmods.dev/skills/hank95/mdpm/pm-start"><img src="https://agentmods.dev/badge/skills/hank95/mdpm/pm-start.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 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 $0.00010 $0.00509
Opus 5 $0.00005 $0.00254
Sonnet 5 $0.00002 $0.00102
Haiku 4.5 $0.00001 $0.00051

Measured 3d ago against content hash a24f80ad9d37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-start 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 3d 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-start/SKILL.md · 37 lines

What it actually says

/pm-start

Move a task into tasks/active/ and officially begin work on it. Argument $ARGUMENTS identifies the task (ID like PRJ-123, or partial title match).

How to run

Delegate to the MDPM CLI — never manipulate task files manually. It handles file moves, work log appends, dep checks, and filename preservation atomically:

python3 "${CLAUDE_PLUGIN_ROOT}/bin/mdpm" --json start $ARGUMENTS

Interpreting the result

The CLI returns JSON with ok, task, changes, warnings. Branch on:

  • ok: false, error: "ambiguous_ref" — the ref matched multiple tasks. The response includes candidates. Print them and ask the user which one they meant.
  • ok: false, error: "not_found" — no match. Suggest /pm-list or /pm-search.
  • ok: false, error: "precondition_failed" — usually unmet dependencies. The message says which ones. Ask the user if they want to start anyway (re-run with --force) or start the dependency first.
  • warnings: ["already active — no change"] — tell the user and show the task's Work Log so they can see where they left off.
  • ok: true — confirm the move. Print the task id, title, and objective. Ask "What do you want to tackle first?"

If the user didn't give a ref

Run python3 "${CLAUDE_PLUGIN_ROOT}/bin/mdpm" list --status backlog and ask which one they want to start. Then re-invoke this skill with that ID.

Notes

  • The CLI already appends "Started work." to the work log. Don't duplicate.
  • Don't move files with mv or edit the status field with sed. The CLI does all of it atomically — if you skip it, you'll leave the repo with the file in active/ but the status: frontmatter still saying backlog, which will confuse /pm-status.
  • Starting a blocked task implies the block is resolved. If status: blocked in the task, ask the user "is the blocker cleared?" before running mdpm start.
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. 3d ago First seen · 37 lines · 10 tokens per session scan A a24f80ad9d37

Subscribe to this mod's changes

pm-start is a skill published in the GitHub repository Hank95/mdpm (3 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 509 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