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 agentmods add skills/dcosson/h2/plan-draftnpx skills add dcosson/h2 --skill plan-draftgit clone --depth 1 https://github.com/dcosson/h2What 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 | $0.00031 | $0.00839 |
| Opus 5 | $0.00015 | $0.00419 |
| Sonnet 5 | $0.00006 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
plan-draft 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Draft
Write a plan doc and its companion test harness doc for a single component.
Inputs
$0: Doc identifier (e.g.,04d-oltp-sql-engine)$1(optional): Scope description — what the plan should cover- Plans directory:
docs/plans/(or the project's established plans directory)
Phase 1: Read Context
- Read
docs/plans/00-plan-index.mdto understand dependencies and scope - Read
docs/plans/00-architecture.mdfor architectural context - Read all prerequisite/dependency docs listed in the plan index for this component
- Read any shaping docs or API contracts referenced
Phase 2: Write Plan Doc
Write docs/plans/$0.md following project conventions:
- Architecture summary with mermaid diagrams (component, sequence, state where relevant)
- Package/module structure and import flow
- API/interface definitions (fully specified, not hand-waved)
- Major types, structs, components with properties and key methods
- Detailed design for all non-trivial algorithms and protocols
- Connected Components — list which other components this plan connects to (its seams), with the interface at each boundary (function signatures, wire protocols, shared types, message formats)
- Acceptance Criteria — 3-8 end-user-facing scenarios that prove the component works in the real system, not just in isolation. Each scenario must cross at least one component boundary. Format: scenario name, steps using the end-user interface (CLI, API, web UI, mobile — whatever the product exposes), expected outcome. These are NOT internal API tests; they verify behavior as a user would experience it.
- Testing section (unit, component, integration strategy). For every test category, specify: (1) where test files will live (exact package/directory paths), (2) which make target or test suite they roll up into, (3) whether they run in CI PR checks, nightly, or on-demand. Tests without a home and a runner don't get run.
- URP (Unreasonably Robust Programming) section — concrete commitments, not wishlists. Each item must specify exactly what will be built, where it fits in the implementation, and how it will be tested. If it's not concrete enough to implement directly from the plan, cut it or make it concrete.
- Extreme Optimization section — same standard: commit to specific techniques with design details, or cut them.
- Alien Artifacts section — same standard: commit to specific techniques with design details, or cut them.
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.
- 2d ago First seen · 66 lines · 31 tokens per session scan A 04752c3537ec
plan-draft is a skill published in the GitHub repository dcosson/h2 (159 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 839 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…