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 prisma/prisma-next --skill write-architecture-docsgit clone --depth 1 https://github.com/prisma/prisma-nextWrote 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/prisma/prisma-next/write-architecture-docs)<a href="https://agentmods.dev/skills/prisma/prisma-next/write-architecture-docs"><img src="https://agentmods.dev/badge/skills/prisma/prisma-next/write-architecture-docs/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/prisma/prisma-next/write-architecture-docs"><img src="https://agentmods.dev/badge/skills/prisma/prisma-next/write-architecture-docs.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 | $0.00055 | $0.01294 |
| Opus 5.5 | $0.00022 | $0.00518 |
| Sonnet 5.5 | $0.00011 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
write-architecture-docs 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.
This is a copy
91% identical to write-architecture-docs — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Architecture Documentation
Architecture docs in this repo serve two audiences: team members working on the system (need precise reference material) and team members seeking context (need an accessible narrative). The doc must work for both without requiring prior project context.
Before writing
- Read at least two sibling docs in the same directory (e.g., other subsystem docs under
docs/architecture docs/subsystems/). Calibrate your voice, structure, and level of detail to match them. - Read the ADRs you'll reference. Don't just link to them — understand them well enough to summarize the key idea inline, so the reader doesn't have to follow the link to understand the doc.
Voice and framing
Write about the system, not the project. These docs describe the intended system as far as we know it. They are not project retrospectives, sprint summaries, or PoC reports.
- State facts: "The execution pipeline generalizes across families" — not "The PoC validated that the execution pipeline generalizes"
- No transient project references: avoid "workstream", "PoC", "sprint", "milestone", "being validated", "current effort"
- No product comparisons: don't reference other products or prior versions. Describe what the system is, not what it improves upon.
- Non-goals are architectural boundaries, not "not yet done" items. No
(current)qualifiers.
Write for a developer without prior context. Imagine someone joining the team and reading this doc as their first exposure to this part of the system.
- Explain why before what. Before introducing a concept like model ownership, explain the problem it solves: "In SQL, related data lives in separate tables and is joined at query time. In MongoDB, the idiomatic pattern is to store related data inside the parent document."
- Let ideas breathe. Don't compress three concepts into one sentence. If a sentence requires the reader to already understand three things to parse it, break it apart.
- Use concrete examples — code snippets, JSON fragments, "a developer writing X gets Y under the hood." Abstract descriptions are hard to pin understanding to.
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 · 73 lines · 55 tokens per session scan A 1c2a99e8dd43
write-architecture-docs is a skill published in the GitHub repository prisma/prisma-next (414 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,294 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to write-architecture-docs, differing in 8 lines, and is treated as a copy.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…