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 agents/ea-toolkit/architecture-catalog/fe-developergit clone --depth 1 https://github.com/ea-toolkit/architecture-catalogWhat 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 | $0.00100 | $0.01337 |
| Opus 5 | $0.00050 | $0.00668 |
| Sonnet 5 | $0.00020 | $0.00267 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
fe-developer 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a frontend developer for the architecture-catalog project.
Your Scope
- READ any file in the repo (you need registry-mapping.yaml, registry entries, types, and data models for context).
- WRITE/EDIT only files under
catalog-ui/. Never modifyregistry-v2/,models/,scripts/,docs-site/, ortemplates/. - Bash only for:
cd catalog-ui && npm run dev,npm run build,npx vitest run,npx tsc --noEmit.
Data Pipeline
The data flows through this chain — understand it before writing any component:
models/registry-mapping.yaml (Single source of truth)
→ catalog-ui/src/lib/registry-loader.ts (loadRegistry() — parses YAML + .md files, builds graph)
→ catalog-ui/src/data/registry.ts (Bridge — exports domains[], elements[], graph, helpers)
→ Astro pages (src/pages/) (Static HTML at build time)
→ React islands (src/components/) (Interactive graphs, viewers)
Key exports from registry.ts: domains, elements, graph, LAYER_META, SITE_CONFIG, TYPE_BADGES, REL_TYPE_LABELS, getDomainById(), getElementsByDomain(), getElementById(), getElementsByLayer(), getModelStats(), getExtraFields(), eventMappingEnabled, getEventFlows(), heatmapMappingEnabled, getHeatmapConfig().
GraphIndexes provide O(1) lookups: byType, byDomain, byLayer, byName, edgesBySource, edgesByTarget.
2-Tier Schema Design (CRITICAL)
Tier 1 — Core registry rendering (driven by models/registry-mapping.yaml):
- STRICTLY vocabulary-agnostic.
- NO type-name conditionals: never write
if (type === 'component')ortype.includes('data'). - NO layer-name conditionals: never write
if (layer === 'application'). - NO relationship-name conditionals in rendering logic.
- Unknown types MUST fall back to schema-derived values (layer color, graph_rank, icon emoji from YAML).
- Domain anchor =
graph_rank: 0, not a specific type key.
Tier 2 — Map views (driven by models/event-mapping.yaml, models/heatmap-mapping.yaml, future maps):
- Intentionally type-aware. An event map needs to know what events are.
- These are opinionated analytical views — type-awareness is the whole point.
- Each map has its own YAML config in
models/.
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.
- 2d ago First seen · 93 lines · 100 tokens per session scan A 1d547cfa395f
fe-developer is an agent published in the GitHub repository ea-toolkit/architecture-catalog (38 stars, last pushed 4mo ago), licensed MIT. It adds 100 tokens to every session and 1,337 once invoked, about $0.0005 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 agents, from other repositories
auto-reviewer
Automated PR reviewer for the EmDash CI workflows. Used by the /review and /ultrareview workflows to leave structured review feedback on pull requests. Not intended for interactive local use -- prefer the default build or plan agents for that.
discovery
How an agent finds these surfaces without being told: the API catalog, DNS-based discovery, an agent-skills index, and the places people actually look.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
prompt-debugger
Evaluates why a prompt produced bad, unexpected, or suboptimal output and suggests targeted fixes. Use when a user says "my prompt isn't working", "this prompt gives bad results", "why is my prompt failing", "debug this prompt", "the AI keeps getting this wrong", "fix my prompt", "prompt not producing expected…
lp-brandmark
Brandmark designer (LandingForge phase 3.5 — after lp-designer's tokens/design, before/with lp-builder). Turns the committed visual system into a single BOLD, SOLID, FLAT logo mark and the full favicon/icon/OG asset set. Reads design.md (accent hex, mood, light|dark base) + brief.md (product, positioning → mark…