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 agentmods add instructions/ea-toolkit/architecture-catalog/claude-mdgit clone --depth 1 https://github.com/ea-toolkit/architecture-catalogWrote 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/instructions/ea-toolkit/architecture-catalog/claude-md)<a href="https://agentmods.dev/instructions/ea-toolkit/architecture-catalog/claude-md"><img src="https://agentmods.dev/badge/instructions/ea-toolkit/architecture-catalog/claude-md.svg" alt="Measured on agentmods" 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 | $0.02891 | $0.02891 |
| Opus 5 | $0.01445 | $0.01445 |
| Sonnet 5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
architecture-catalog CLAUDE.md 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 4d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
What is this project?
A lightweight, Git-native architecture catalog. It replaces monolithic tools like Archi with a simple repo structure: architecture elements are registered as Markdown files, diagrams are draw.io files, and Python scripts validate, extract, refresh, and generate dashboards.
The goal is to be an open-source, lightweight alternative for architects who want Git-friendly, AI-readable architecture models without learning a DSL or paying for enterprise tooling.
Architecture (how it works)
registry-mapping.yaml ──→ registry-loader.ts ──→ Astro pages
(schema: types, (reads .md files, (static HTML
fields, relationships) resolves refs, at build time)
builds graph)
Single source of truth: models/registry-mapping.yaml drives everything — the UI, validation, and data loading. Adding a new element type = add one entry to this YAML file + create a _template.md. Zero code changes.
Data pipeline: registry-mapping.yaml → registry-loader.ts (loadRegistry()) → registry.ts (bridge) → Astro pages. The loader builds an in-memory graph with elements, edges, and indexes (byType, byDomain, byLayer).
Key design: Framework-agnostic. ArchiMate alignment is optional, not required. Works with any architecture vocabulary. Layers are flat (1 to N), each with sub-folders for element types. No nested child layers.
Current State
Registry (registry-v2/)
- 4-layer structure — flat layers, each with typed sub-folders
- Template-driven — each element type has a
_template.mdwith typed YAML frontmatter - Example domains: "Customer Management", "Billing & Payments", "Analytics & Insights" — 3 fictional B2B SaaS CRM domains with 71 elements across all 4 layers
- Health: 71 healthy, 71 connected, 0 orphans, 0 broken refs, 84 pages
Catalog UI (catalog-ui/)
- Astro 5 + React static site for browsing the registry
- Schema-driven — all types, layers, and relationships derived from
models/registry-mapping.yaml - ReactFlow graphs for visualizing element relationships (via
@xyflow/react+ dagre) - Diagram viewer supporting PlantUML, BPMN, and draw.io formats
- CSS pattern: EventCatalog-inspired RGB variable pattern:
--ec-page-bg: 255 255 255used asrgb(var(--ec-page-bg)) - 3-panel layout: icon bar (56px) + nested sidebar (315px) + main content
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.
- 4d ago First seen · 237 lines · 2,891 tokens per session scan A 8998da6137a3
architecture-catalog CLAUDE.md is an instructions file published in the GitHub repository ea-toolkit/architecture-catalog (38 stars, last pushed 4mo ago), licensed MIT. It adds 2,891 tokens to every session, about $0.0145 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 instructions, from other repositories
emdash AGENTS.md
AGENTS.md instructions for emdash-cms/emdash, covering rules, workflow, architecture, code patterns and database: never interpolate into sql.
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
stardrive AGENTS.md
Instructions for peltmonger/stardrive, covering 🛑 critical: repository bootstrap directive 🛑, general information and guidelines for ai agents, analyze your high-level use case first, how the .ai guidance files relate and this is an astro project.
minshop AGENTS.md
Instructions for ddyy/minshop, covering agents.md — working on minshop, the loop (run this constantly), inspecting local data: use local explorer, not the cli, customizing a cloned shop and architecture in one screen.
seo-graph AGENTS.md
Instructions for jdevalk/seo-graph, covering agents.md — seo-graph, what this library does, architecture, installation and astro projects — install both.
pr-lens AGENTS.md
AGENTS.md instructions for coldteadotai/pr-lens, covering pr lens — agent instructions, hard requirements, general, 1. think before coding and 2. simplicity first.