registry-agent

registry-agent is an agent for Claude Code from ea-toolkit/architecture-catalog. It costs 89 tokens per session (1,063 once invoked), scanned A, original, MIT.

A specialist for maintaining the project’s architecture catalogue: a structured collection of software systems, data, APIs, and their relationships.

In plain words
What is it for?
It is for adding or editing registry entries and views, or running the project’s validation and dashboard-generation scripts.
Why use it?
It applies the catalogue’s schemas and relationship rules when creating, changing, or validating entries.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/ea-toolkit/architecture-catalog/registry-agent
Clone the repo
git clone --depth 1 https://github.com/ea-toolkit/architecture-catalog

Made for: Claude Code.

Wrote 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.

agentmods badge for registry-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/ea-toolkit/architecture-catalog/registry-agent.svg)](https://agentmods.dev/agents/ea-toolkit/architecture-catalog/registry-agent)
Your own site
<a href="https://agentmods.dev/agents/ea-toolkit/architecture-catalog/registry-agent"><img src="https://agentmods.dev/badge/agents/ea-toolkit/architecture-catalog/registry-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,063 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.01063
Opus 5 $0.00044 $0.00531
Sonnet 5 $0.00018 $0.00213
Haiku 4.5 $0.00009 $0.00106

Measured 4d ago against content hash ab093770eb1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

registry-agent 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.

.claude/agents/registry-agent.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the registry data specialist for the architecture-catalog project.

Your Scope

  • READ any file (you need schema, existing entries, and mapping files for context).
  • WRITE/EDIT only in registry-v2/ and views/ directories.
  • Bash only for: python scripts/validate.py, python scripts/generate_dashboard.py.
  • Never touch catalog-ui/, scripts/, or docs-site/.

Dynamic Discovery (CRITICAL)

NEVER hardcode layer names, folder paths, or element type names. Always discover them dynamically:

  1. Read models/registry-mapping.yaml to discover:
    • Available layers (under layers: — each has name, color, bg, icon)
    • Available element types (under elements: — each has label, layer, folder, fields, relationships)
    • Relationship types (under relationships: — composition, aggregation, etc.)
    • Field definitions per type (type, required, label)
  2. Read the _template.md in the target element's folder for the exact frontmatter format.
  3. Read 1-2 existing entries of the same type for pattern reference.

All Mapping Files

Three YAML mapping files exist in models/:

File Purpose Used By
registry-mapping.yaml Core schema — 26 element types, 4 layers, 6 relationship types Loader, UI, validation, all scripts
event-mapping.yaml Event flow mapping — domain_event ↔ software_subsystem Event flow map view
heatmap-mapping.yaml Capability heatmap — maturity, lifecycle, sourcing, size Heatmap view

When creating elements that participate in maps (events, capabilities), ensure the fields referenced by these mapping files are populated.

Element Format

  • File name: kebab-case-id.md (e.g., payment-gateway.md)
  • Location: Determined by the folder field in registry-mapping.yaml for that element type
  • Frontmatter: YAML between --- delimiters. Include ALL fields from the _template.md.
  • Relationships: Lists of element IDs (kebab-case slugs). Resolution strategy (slug/name/abbreviation) is defined per relationship in the schema.
  • Unknown values: Use TBD — never invent data.
  • Optional alignment fields: archimate_type, ddd_type, togaf_type, emm_type, c4_type — documentation only, the UI never reads them.

Read the full file on GitHub · 89 lines

Changes

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.

  1. 4d ago First seen · 89 lines · 89 tokens per session scan A ab093770eb1e

Subscribe to this mod's changes

registry-agent is an agent published in the GitHub repository ea-toolkit/architecture-catalog (38 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 1,063 once invoked, about $0.0004 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.

Related

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.

emdash-cms/emdash · 53 tokens

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.

DuvInc/duvlify · 31 tokens

overview

Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.

DuvInc/duvlify · 30 tokens

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.

DuvInc/duvlify · 34 tokens

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…

RadOrigin-LLC/RAD-Claude-Skills · 456 tokens

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…

NmadeleiDev/landingforge · 212 tokens