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-do)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-do"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-do/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-do"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-do.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 | $0.00072 | $0.06297 |
| Opus 5 | $0.00036 | $0.03148 |
| Sonnet 5 | $0.00014 | $0.01259 |
| Haiku 4.5 | $0.00007 | $0.00630 |
Grade A, and why
plan-do 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-do
Pick up a saved plan from ~/plans/<repo>/ and route it to the right next step in the planning pipeline. The bundled plan_keeper_cli.py handles listing (repo derivation, newest-first sort, empty-state fallback); this skill classifies the picked plan and routes to the matching next skill.
The skill is the entry point that joins this pipeline at the right stage:
idea ──► brainstorming ──► spec ──► writing-plans ──► implementation plan ──┬──► executing-plans (sequential, review-gated)
├──► task-list-builder ──► task-list-runner (dispatched tasks)
└──► autonomous (AFK, no human, ──► PR)
For plans that aren't execution-ready yet (idea, spec), the skill suggests the single next pipeline stage. For execution-ready plans, it offers all three execution engines at once — recommended first — and the user picks how hands-off they want to be.
Quick reference
- Lists: the not-yet-started plans only:
Status: todoandStatus: backlog(list --sections todo,backlog). In-progress / in-review / done plans are excluded (you're picking something to start). Classified.mdplans carry a--<kind>suffix in their filename (e.g.…-noun-first-provider-commands--design.md); this is expected. The picker resolves the filename from the numbered row (N. <filename>). - Human view: to show a project's stages clustered (design → exec-plan) rather than the flat startable list, run
list --group(mutually exclusive with--sections). That's a presentation aid; the--sections todo,backlogform below is what this skill pastes and parses. - Writes: one frontmatter update when it starts a plan (step 7) — flips
Statustoin-progressand clears theAgenttag (so groundcrew won't claim a plan you're driving). It never moves, deletes, or rewrites the body. - Worktree refresh: before handing off (step 6), it fast-forwards the current repo onto its base branch (
main/master) — automatically, no confirmation — but only when the worktree is untouched (clean tree and no commits ahead of base), so the update is always a conflict-free fast-forward. Dirty or ahead branches are left as-is. This is the current repo only, not the fullupdate-git-reposskill. <repo>: auto-derived or override — see ../../repo-derivation.md.- Classification (tier 1, readiness): idea / spec / execution-ready. Read the plan's
Kind:frontmatter first (authoritative — see ../../plan-kinds.md); infer from content only whenKindis absent. - Classification (tier 2, shape — only for execution-ready): picks which of the three execution engines to recommend first; all three are always offered.
- Routing:
superpowers:brainstorming(idea),superpowers:writing-plans(spec). Execution-ready → menu ofautonomous:autonomous,harness:task-list-builder→task-list-runner,superpowers:executing-plans. - Confirmation: required before reading any plan file and before invoking any next skill.
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.
- 9d ago First seen · 268 lines · 72 tokens per session scan A 8bf456677e50
plan-do is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 21d ago), licensed MIT. It adds 72 tokens to every session and 6,297 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…