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 MartinPLarsen/claude-architecture-skills --skill architecture-mapgit clone --depth 1 https://github.com/MartinPLarsen/claude-architecture-skillsWrote 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/martinplarsen/claude-architecture-skills/architecture-map)<a href="https://agentmods.dev/skills/martinplarsen/claude-architecture-skills/architecture-map"><img src="https://agentmods.dev/badge/skills/martinplarsen/claude-architecture-skills/architecture-map/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/martinplarsen/claude-architecture-skills/architecture-map"><img src="https://agentmods.dev/badge/skills/martinplarsen/claude-architecture-skills/architecture-map.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 | $0.00163 | $0.01364 |
| Opus 5 | $0.00081 | $0.00682 |
| Sonnet 5 | $0.00033 | $0.00273 |
| Haiku 4.5 | $0.00016 | $0.00136 |
Grade A, and why
architecture-map 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Map
Produce / update <repo>/architecture-map/ — an interactive HTML-card + SVG viewer of
the architecture (the Claude Design template), backed by a single data file the agent owns.
Family
Pipeline: architecture-audit (verified nodes/edges) → architecture-map (this — the
interactive map) → architecture-grill (grow the map live while grilling a plan) →
architecture-cleanup (mark dead/removable code red on the map) → architecture-improve
(amber optimisation proposals). This skill maps how parts connect and what flows between them;
dead-code / orphan detection lives in architecture-cleanup, not here.
When NOT to use
SKIP for a one-off static diagram or a text architecture summary — run architecture-audit
directly. Reach for THIS skill only when you want a persistent, clickable map you revisit and plan on.
Two modes (same artifact)
- Kortlæg — audit an existing repo, fill the map.
- Planlæg — open the map, add
proposednodes/edges while discussing a change.
Procedure
A. Gather the data (Kortlæg)
- Run the
architecture-auditskill's Map phase (Phase 0 scout + Phase 1 parallel readers). You want the structured per-subsystem result, not the Markdown doc — each reader returns components (id, label, status, role, filespath:line) andA --> B: labeledges. - Transform that into the map data contract (
references/map-schema.md): subsystems, nodes, edges. Setsource: "audit"and stampgeneratedAtwith the current ISO time. For each node, write the node-card fields so a non-technical reader gets it:label= a descriptive plain-language name (what it does), NOT the raw function name.tech= the technical identifier (function / endpoint / file).engine= the motor category (llm,image,db, … — seereferences/map-schema.mdfor the canonical 14-key enum; don't restate it here) + optionalengineLabelfor the specific name (e.g."OpenRouter · Claude Sonnet 4.6").input/processing/output= plain language. Deriveinputfrom the node's incoming edges,outputfrom its outgoing edges,processingfromrole.
- Write it as a temp fresh JSON:
/tmp/arch-fresh.json.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 87 lines · 0 tokens per session scan A b0089eaf17bc
architecture-map is a skill published in the GitHub repository MartinPLarsen/claude-architecture-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 1,364 once invoked, about $0.0008 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 2026-08-31.
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…
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…