Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add muhimu/claude-plan-lifecycle --skill plan-frontmattergit clone --depth 1 https://github.com/muhimu/claude-plan-lifecycleWrote 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/muhimu/claude-plan-lifecycle/plan-frontmatter)<a href="https://agentmods.dev/skills/muhimu/claude-plan-lifecycle/plan-frontmatter"><img src="https://agentmods.dev/badge/skills/muhimu/claude-plan-lifecycle/plan-frontmatter.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.01899 |
| Opus 5 | $0.00026 | $0.00949 |
| Sonnet 5 | $0.00010 | $0.00380 |
| Haiku 4.5 | $0.00005 | $0.00190 |
Grade A, and why
plan-frontmatter 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 6d 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 Frontmatter
Every plan or design doc written to the plans dir (resolved per the plans-dir
convention: PLANS_DIR env, else git config plans.dir, else default
local/plans/) starts with YAML frontmatter:
---
title: <human-readable name of the effort>
slug: <kebab-case key, SHARED across all files of one effort>
issue: <root issue — bare number for same-repo, org/repo#N for cross-repo>
status: draft
pr:
---
Fields
- title — human-readable name. Informational only; no tooling reads it.
- slug — the grouping key. A design doc and its implementation plan (and any
follow-up docs) for the SAME unit of work carry the SAME slug.
reap-plansgroups files by slug and reaps a whole group together. Pick the slug once (kebab-case, e.g.split-state-enum) and reuse it verbatim on every related file. - issue — the root issue the effort addresses. Bare number (
issue: 3178) for an issue in the same repo;org/repo#Nform for cross-repo. Shared across the slug group liketitle. Leave empty (issue:) only when the work genuinely traces to no issue. When set, two things follow:- The plan body's header block states the root issue with a one-line mechanism summary — a reader must not need to open GitHub to know what problem the plan solves.
- The PR that ships the plan MUST include
Closes #<N>(orCloses org/repo#N) on the first line of its body, so the merge auto-closes the issue. For stacked PRs, ONLY the tip PR carries theClosesline — under the squash cascade the tip merges last, so tip-merged ⇔ effort done; an earlier slice must not close the issue prematurely./execute-planenforces this when it opens PRs.
- status — one of
draft|in-progress|merged|abandoned. A bare plain scalar — no quotes (status: draft, notstatus: "draft"). - pr — the PR number once a PR is opened, as a bare number (
pr: 2297) — it is a YAML integer, so no quotes and no#. Leave empty (pr:, parses as null) until then. (reap-planstolerates a stray quote or leading#, but the clean form is the bare number.)
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.
- 6d ago First seen · 151 lines · 52 tokens per session scan A 289631b46a63
plan-frontmatter is a skill published in the GitHub repository muhimu/claude-plan-lifecycle (2 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 1,899 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…