plan-crew

plan-crew is a skill for Claude Code from paulbaranowski/wild-horses. It costs 91 tokens per session (3,519 once invoked), scanned C, original, MIT.

A queue manager for saved work plans across code repositories. It lets you view plans waiting for dispatch and move them between backlog and to-do states.

In plain words
What is it for?
Use it to list queued plans, add plans to the groundcrew pickup queue in bulk, or remove them from that queue.
Why use it?
It removes the need to edit plan files one by one when deciding what work should be picked up next. It also makes the current repository’s queue, or all repositories’ queues, easy to inspect.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the plan-keeper plugin — 9 skills shipped together

Good fit Use it to list queued plans, add plans to the groundcrew pickup queue in bulk, or remove them from that queue.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add paulbaranowski/wild-horses
Claude Code
/plugin install plan-keeper

Made for: Claude Code.

Or install plan-keeper, the plugin that ships this one along with the rest of its 9 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 plan-crew

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-crew/github.svg)](https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-crew)
Your own site
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-crew"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-crew/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.

agentmods 80×15 button for plan-crew

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-crew"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-crew.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,519 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.03519
Opus 5 $0.00046 $0.01759
Sonnet 5 $0.00018 $0.00704
Haiku 4.5 $0.00009 $0.00352

Measured 10d ago against content hash 1063e2ae9264, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

plan-crew scanned grade C with 1 finding 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 10d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- prettier-ignore -->
plugins/plan-keeper/skills/plan-crew/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plan-crew

Show the groundcrew dispatch queue — by default the current repo's plans, or every repo under ~/plans/ on request — and manage it both directions in bulk: promote backlog → todo (add to the queue) and dequeue todo → backlog (pull out). Backed by three plan_keeper_cli.py subcommands: crew queue list (the scoped read), crew queue add (promote → todo), and crew queue drop (dequeue → backlog). Both writers address plans by bare filename within a --repo, so you act on each repo's selections with one call per direction.

Quick reference

  • Scope: the current repo by default (crew queue list); --all lists every repo, --repo <name> lists one named repo. See Choosing the scope.
  • Reads: ~/plans/<repo>/*.md with frontmatter (one level deep; done/, deferred/ excluded), filtered to the resolved scope.
  • Writes: frontmatter Status (and, on promote, Agent when missing, plus a minted Plan-keeper Ticket when absent) — atomic per file.
  • Plan-keeper ticket mint: on promote, the plan's Plan-keeper Ticket (plan-<digits>, minted once and frozen) is written if absent, so the dispatch id is visible the moment a plan is queued. Any Linear Ticket / Jira Ticket the plan carries is left untouched (the three ids coexist).
  • Dispatch has several gates; the Agent tag is the one this skill manages. groundcrew dispatches a plan only when all of these hold at once:
    1. it lives in a ~/plans/<repo>/ bucket (active — not done//deferred/) whose repo is registered in groundcrew's workspace.knownRepositories;
    2. its Status is todo;
    3. it carries an Agent tag;
    4. it isn't held by an unfinished Blocked-by prerequisite. The Agent gate (3) is the one plan-crew writes — and the one most often missing, because groundcrew skips every agent-less plan in every status, including todo (there is no implicit "default to claude"; an agent-less plan is never dispatched). So crew queue add, which stamps Agent: claude when missing, is what actually makes a plan dispatchable, not merely what makes it visible. The repo-registration gate (1) lives in groundcrew's own config and is outside what plan-crew can set — see ../../groundcrew/README.md.
  • Promote is the only automatic Agent writer. crew queue add writes Agent: claude on a plan that has none (a plan that already names an Agent keeps it). Nothing else stamps it: plan-save no longer adds it at birth, plan-do strips it when you start a plan locally, and plan-split leaves its slices agent-less. So the tag's presence means "queued for groundcrew," and nothing adds it behind your back. The flip side: a todo plan can reach this queue agent-less (e.g. a plan-split slice promoted to todo but never queued through here), and such a plan is not dispatchable until you queue it through plan-crew to stamp the Agent.
  • Confirmation: required before any mutation.
  • Sibling: plan-update is the targeted single-plan frontmatter editor; plan-crew is its multi-select counterpart and the only one that spans repos (with --all). Both can promote a single plan — use plan-update when you already have one specific plan in hand, plan-crew when browsing the queue.

Read the full file on GitHub · 194 lines

Files

What ships with it

1 file 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. 10d ago First seen · 194 lines · 91 tokens per session scan C 1063e2ae9264

Subscribe to this mod's changes

plan-crew is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 22d ago), licensed MIT. It adds 91 tokens to every session and 3,519 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). 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