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 dcosson/h2 --skill plan-seam-reviewgit clone --depth 1 https://github.com/dcosson/h2Wrote 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/dcosson/h2/plan-seam-review)<a href="https://agentmods.dev/skills/dcosson/h2/plan-seam-review"><img src="https://agentmods.dev/badge/skills/dcosson/h2/plan-seam-review/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/dcosson/h2/plan-seam-review"><img src="https://agentmods.dev/badge/skills/dcosson/h2/plan-seam-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.03901 |
| Opus 5 | $0.00030 | $0.01951 |
| Sonnet 5 | $0.00012 | $0.00780 |
| Haiku 4.5 | $0.00006 | $0.00390 |
Grade A, and why
plan-seam-review 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Seam Review
Review the interfaces and seams between connected plan components. Individual plan reviews catch problems within a single doc; seam reviews catch problems between docs — mismatched interfaces, incompatible assumptions, lifecycle ordering gaps, and acceptance criteria that silently depend on contracts defined differently elsewhere.
This skill runs after individual plan reviews have converged (plan docs have been reviewed and revised), and before plan-to-beads decomposes work into implementation tasks.
Inputs
$0: Review mode —verticalorhorizontal$1: Seam specification (depends on mode, see below)$2: Reviewer identifier (e.g.,reviewer-1, used in output filename)- Plans directory:
docs/plans/(or the project's established plans directory)
Mode: Vertical Slice
A vertical slice follows a single request or workflow end-to-end through the stack, crossing every component boundary along the way.
$1 is a short name for the slice (e.g., user-login-flow, create-record, file-upload). The reviewer identifies the relevant plan docs by tracing the request path from the user-facing entry point through every internal component to the final response/side-effect.
Example slices:
- A web request through gateway, auth, business logic, storage, and back
- A CLI command through argument parsing, config loading, execution engine, and output formatting
- A mobile action through UI layer, API client, backend endpoint, and push notification
Mode: Horizontal Seam
A horizontal seam checks one cross-cutting contract or interface against all components that implement or consume it.
$1 is a short name for the seam (e.g., lifecycle-contract, config-schema, error-format, auth-context). The reviewer identifies all plan docs that reference this contract and checks each one for consistency.
Example seams:
- A lifecycle interface (init/start/stop/health) that multiple components must implement
- A configuration schema that multiple components read from
- An error handling contract (error types, codes, retry semantics) that crosses component boundaries
- An authentication/authorization context that flows through the system
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 · 291 lines · 59 tokens per session scan A 3f2a2bab5589
plan-seam-review is a skill published in the GitHub repository dcosson/h2 (159 stars, last pushed 13d ago), licensed MIT. It adds 59 tokens to every session and 3,901 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…