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 joao-aires/agent-skills-public --skill architecture-documentationgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/architecture-documentation)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/architecture-documentation"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/architecture-documentation/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/joao-aires/agent-skills-public/architecture-documentation"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/architecture-documentation.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 | $0.00052 | $0.01289 |
| Opus 5.5 | $0.00021 | $0.00516 |
| Sonnet 5.5 | $0.00010 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
architecture-documentation 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read composition guidance and apply documentation-writing for authoring quality.
Explain architecture through useful views
Make the system's structure, behaviour and consequences understandable from evidence. Topic mentions, technology lists and diagrams alone are insufficient. Work within the requested documentation/design scope; findings do not authorize refactoring or deploying a system.
Establish the baseline and questions
Read the product/quality requirements, accepted decisions, existing documentation and relevant code/configuration. Identify whether the view describes implemented code, a configured topology, an accepted design or a proposal. Mark uncertainty instead of inferring deployment or control effectiveness from configuration.
For a whole-system review, use arc42 as a coverage check: drivers/constraints, context, strategy, building blocks, runtime, deployment, cross-cutting concepts, decisions, quality scenarios, risks/debt and vocabulary. Link existing authorities rather than copying requirements, schemas and runbooks or imposing twelve new files. For a bounded change, maintain the affected views only.
Model structure and responsibilities
Use C4 context and containers for the baseline, then selected component views where detail resolves ambiguity or risk. A container is an application/data store, not necessarily a Docker container. A component view zooms into one container; a code diagram is rarely needed for routine architectural explanation.
Explain each meaningful building block in relation to the work it performs. State which part of the user or system outcome it owns, how another component invokes it, what state it controls, and why it depends on its neighbors. Link the code location so a contributor can follow the explanation into the implementation.
Describe the actual decomposition, including mixed legacy handlers, coupling and incomplete abstractions. When a responsibility is spread across components, show that fact and its consequence instead of drawing a cleaner desired layer as though it exists. Keep in-process libraries distinct from independently running services.
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.
- yesterday Changed · +24 lines c0f9e6b2c782
- 2d ago Changed 26eec03140ab
- 5d ago First seen · 67 lines · 52 tokens per session scan A 8ed531e379bc
architecture-documentation is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,289 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 2026-10-17.
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…