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-done)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-done"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-done/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-done"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-done.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 | $0.00054 | $0.02476 |
| Opus 5 | $0.00027 | $0.01238 |
| Sonnet 5 | $0.00011 | $0.00495 |
| Haiku 4.5 | $0.00005 | $0.00248 |
Grade A, and why
plan-done 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 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.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-done
Archive a completed plan from ~/plans/<repo>/ into ~/plans/<repo>/done/, with a Completed on: date written into the file's frontmatter. The bundled plan_keeper_cli.py handles the actual stamp-and-move (atomic write to done/, then unlink the source). This skill identifies which plan to archive, confirms only when it had to infer the plan (rather than the user naming it), and handles collisions.
Quick reference
- Moves:
~/plans/<repo>/<file>.md→~/plans/<repo>/done/<file>.md. - Stamp: the CLI writes
Completed on: YYYY-MM-DDinto the YAML frontmatter at the top of the archived file. - Identifier: a filename (
--file) or a ticket id (--ticket) — see step 1 and step 3. <repo>: auto-derived or override — see ../../repo-derivation.md.- Collision in
done/: ask the user; never overwrite silently. - Confirmation: skipped when the user names the plan (filename or ticket id) or picks it from the listing; required only when the skill inferred the plan from conversation context.
Procedure
Follow these steps in order. Do not skip steps.
1. Identify the plan to archive
Prefer conversation context; fall back to a CLI listing.
First, check the user's invocation for a repo override. Recognize:
- "done with the
<name>plan" - "plan-done
<name>" - "archive the plan in
<name>" - "in the
<name>folder/bucket"
If present, extract <name> and pass --override <name> to all CLI calls below.
If the user names the plan by a ticket id (e.g. plan-195296912509085, ENG-123) instead of a filename, skip the listing and archive it directly with --ticket <id> in step 3. Resolution matches any of the plan's id fields (Plan-keeper Ticket / Linear Ticket / Jira Ticket) globally across ~/plans/, so no --override is needed; the CLI exits 3 when no active plan carries that ticket and exits 2 (listing candidates) when more than one does.
Look for a clear plan candidate from this session:
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 · 151 lines · 54 tokens per session scan A fee9572edfa0
plan-done is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 2,476 once invoked, about $0.0003 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…