agent-registry

A project-specific registry describing available coding agents, their service tiers, and the kinds of work each agent handles.

In plain words
What is it for?
Use it when planning work across roles such as architecture, security, development, testing, data engineering, content, or performance.
Why use it?
It gives the assistant a shared reference for assigning tasks to suitable specialists and choosing an appropriate tier.

Agent

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/monkilabs/opencastle/agent-registry
Clone the repo
git clone --depth 1 https://github.com/monkilabs/opencastle
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00000 $0.00468
Opus 5 $0.00000 $0.00234
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured 2d ago against content hash c4577b4caf4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-registry 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.

src/orchestrator/customizations/agents/agent-registry.md · 46 lines

What it actually says

# Agent Registry

Project-specific agent tiers and scope examples referenced by the `team-lead-reference` skill.

<!-- Populated by `opencastle init` based on project structure. -->

## Specialist Agent Registry

Tiers describe what kind of model the work wants. Your assistant picks the actual
model — it knows which ones your account can reach and what they cost today.

| Agent | Tier | Best For |
|-------|------|----------|
| **Team Lead** | Premium | Decomposing work, delegating, verifying results |
| **Architect** | Premium | Architecture decisions, ADRs, critical review |
| **Security Expert** | Premium | Auth, access policies, headers, input validation |
| **Developer** | Standard | Features, pages, components, routing, API routes and contracts |
| **UI/UX Expert** | Standard | Components, styling, accessibility, frontend design |
| **Data Engineer** | Standard | Migrations, access policies, query performance, ETL pipelines, imports |
| **Content Engineer** | Standard | CMS schema, content types, content queries |
| **Testing Expert** | Standard | E2E and integration tests, browser validation |
| **Performance Expert** | Standard | Bundle size, Core Web Vitals, profiling |
| **DevOps & Release** | Standard | Deployments, CI/CD, cron jobs, pre-release verification, changelogs |
| **Researcher** | Standard | Codebase exploration, pattern discovery, git archaeology |
| **Writer** | Economy | UI copy, error messages, docs, roadmaps, meta tags, structured data |
| **Reviewer** | Economy | Fast review after every delegation |

## Deepen-Plan Scope Examples

<!-- Customize these paths to match your project structure.
     When running the Deepen-Plan protocol, split research by domain: -->

```
Researcher A: "Research database/backend aspects of [feature]"
  Scope: <database-migrations-dir>/, <server-libs>/

Researcher B: "Research frontend/UI aspects of [feature]"
  Scope: <ui-libs>/, <app-dir>/

Researcher C: "Research CMS/content aspects of [feature]"
  Scope: <cms-dir>/, <queries-lib>/
```

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. 2d ago First seen · 46 lines · 0 tokens per session scan A c4577b4caf4f

Subscribe to this mod's changes

agent-registry is an agent published in the GitHub repository monkilabs/opencastle (61 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 tokens. 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.