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.
/plugin marketplace add paulbaranowski/wild-horses/plugin install plan-keeperWrote 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.
[](https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-crew)<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.
<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>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.
| Model | Per session | Once 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 |
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 --> 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);--alllists every repo,--repo <name>lists one named repo. See Choosing the scope. - Reads:
~/plans/<repo>/*.mdwith frontmatter (one level deep;done/,deferred/excluded), filtered to the resolved scope. - Writes: frontmatter
Status(and, on promote,Agentwhen missing, plus a mintedPlan-keeper Ticketwhen 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. AnyLinear Ticket/Jira Ticketthe plan carries is left untouched (the three ids coexist). - Dispatch has several gates; the
Agenttag is the one this skill manages. groundcrew dispatches a plan only when all of these hold at once:- it lives in a
~/plans/<repo>/bucket (active — notdone//deferred/) whose repo is registered in groundcrew'sworkspace.knownRepositories; - its
Statusistodo; - it carries an
Agenttag; - it isn't held by an unfinished
Blocked-byprerequisite. TheAgentgate (3) is the one plan-crew writes — and the one most often missing, because groundcrew skips every agent-less plan in every status, includingtodo(there is no implicit "default to claude"; an agent-less plan is never dispatched). Socrew queue add, which stampsAgent: claudewhen 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.
- it lives in a
- Promote is the only automatic
Agentwriter.crew queue addwritesAgent: claudeon a plan that has none (a plan that already names an Agent keeps it). Nothing else stamps it:plan-saveno longer adds it at birth,plan-dostrips it when you start a plan locally, andplan-splitleaves its slices agent-less. So the tag's presence means "queued for groundcrew," and nothing adds it behind your back. The flip side: atodoplan can reach this queue agent-less (e.g. a plan-split slice promoted totodobut never queued through here), and such a plan is not dispatchable until you queue it through plan-crew to stamp theAgent. - Confirmation: required before any mutation.
- Sibling:
plan-updateis 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.
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.
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.
- 10d ago First seen · 194 lines · 91 tokens per session scan C 1063e2ae9264
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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.