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-update)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-update"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-update/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-update"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-update.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 | $0.00065 | $0.01958 |
| Opus 5 | $0.00032 | $0.00979 |
| Sonnet 5 | $0.00013 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
plan-update 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-update
Edit the frontmatter of an existing plan in ~/plans/<repo>/. The bundled plan_keeper_cli.py file-meta set does the atomic write — one self-documenting flag per field; this skill's job is to identify the plan, identify which field(s) to change, and route to the CLI after user confirmation.
Quick reference
- Target:
~/plans/<repo>/<filename>(active state — notdone/ordeferred/). - Field → flag:
Agent→--agent,Status→--status,Kind→--kind,Completed on→--completed-on,Plan-keeper Ticket→--plankeeper-ticket,Linear Ticket→--linear-ticket,Jira Ticket→--jira-ticket. (--ticketis not a value flag — it locates a plan by any of its id fields, like push; write an id with the matching per-system flag.) --statusis lifecycle-aware: active states (backlog/todo/in-progress/in-review) rewrite in place, but--status done/--status deferredrelocate the plan intodone//deferred/(anddonestampsCompleted on) — exactly whatplan-donedoes. Preferplan-donefor completing a plan; reach here fordone/deferredonly when editing other fields in the same breath.- Status vocabulary:
backlog(default; fetched but not dispatched — confirm viacrew status <id>),todo(the status gate for dispatch — but not sufficient alone: groundcrew also requires anAgent:tag and a registered repo, see ../../groundcrew/README.md),in-progress(set by groundcrew's markInProgress hook),in-review(set by groundcrew's markInReview hook when the PR opens),done(set by plan-done when archiving). The middle values (in-progress,in-review,done) are normally written by the system — set them by hand only if you know why. - Kind vocabulary:
idea/prd/reqs/design/spec/exec-plan— the document type, validated against this closed set (see ../../plan-kinds.md, including its "Choosing the right Kind" decision procedure). Set byplan-save; correct it here if it was inferred wrong. Changing--kindrenames the file's--<kind>segment to match (frontmatter stays the source of truth), so the path changes and the CLI prints the new one. - Common edits:
- Promote:
--status todosets the status gate; groundcrew won't dispatch until the plan also has anAgent:tag, so pair it with--agent claude(or queue viaplan-crew, which stamps the Agent for you). - Change model:
--agent codex. - Reset:
--status backlog. - Reclassify:
--kind exec-plan(changes howplan-doroutes the plan, and renames the--<kind>filename segment to match).
- Promote:
- Confirmation: required before any mutation.
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 · 103 lines · 65 tokens per session scan A 7abe2a10fec3
plan-update is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 21d ago), licensed MIT. It adds 65 tokens to every session and 1,958 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…