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-architectgit 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-architect)<a href="https://agentmods.dev/skills/dcosson/h2/plan-architect"><img src="https://agentmods.dev/badge/skills/dcosson/h2/plan-architect/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-architect"><img src="https://agentmods.dev/badge/skills/dcosson/h2/plan-architect.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 | $0.00049 | $0.01505 |
| Opus 5.5 | $0.00020 | $0.00602 |
| Sonnet 5.5 | $0.00010 | $0.00301 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
plan-architect 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Architect
Produce a high-level architecture doc and determine whether the project needs a single plan doc or multiple sub-plans. If multiple, produce a plan index listing what sub-plans need to be written (but do NOT write the sub-plans — those are written later via /plan-draft).
Inputs
$0: Path to shaping doc or requirements source (required)- Plans will be written to
docs/plans/(or the project's established plans directory)
Phase 1: Read & Understand
- Read the shaping doc at
$0thoroughly - Read any referenced documents (prior art, API contracts, reviews, design docs)
- Identify the key architectural decisions, components, deployment modes, and cross-cutting concerns
- Note any open questions, ambiguities, or unresolved decisions from the shaping process
Phase 2: Resolve Open Questions
Before writing anything, check for unresolved questions from the shaping doc or requirements:
- Unresolved architectural decisions (e.g., which protocol, which storage backend)
- Ambiguous requirements (e.g., "support high availability" without defining SLOs)
- Missing context (e.g., deployment constraints, team size, timeline expectations)
- Contradictions between different parts of the requirements
Resolve these BEFORE proceeding. Ask questions directly inline in your response text, or via h2 send if communicating through h2 messaging. Do NOT use the AskUserQuestion tool — communicate questions conversationally in your output or via h2 messages. Do not paper over ambiguity — surface it now. It's much cheaper to resolve questions at this stage than after detailed plans are written.
Phase 3: Write Architecture Doc
Write docs/plans/00-architecture.md covering:
- System overview and goals
- Component diagram (mermaid)
- Tier/layer decomposition
- Deployment modes (single-node, distributed, etc.)
- Data flow diagrams for key paths (mermaid sequence diagrams)
- CAP / consistency properties
- Cross-cutting concerns (security, observability, multi-tenancy)
- Key architectural decisions with rationale
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.
- 1mo ago First seen · 118 lines · 49 tokens per session scan A 573d306bc8f8
plan-architect is a skill published in the GitHub repository dcosson/h2 (163 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,505 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
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…
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…