agent-registry

agent-registry is a skill for Claude Code, Codex from sonichi/sutando. It costs 66 tokens per session (1,092 once invoked), scanned A, original, MIT.

A small local service that keeps a live list of coding-agent sessions. Agents register when they start and send regular heartbeat signals while running; other tools can read the list through a local web interface.

In plain words
What is it for?
Use it to register, monitor, list, watch, or remove agent sessions, and optionally mirror that information to an AG2 Workforce Hub.
Why use it?
It lets you see which agents are active, where they are running, and when they started without relying on a remote service. It works offline and stores its data in SQLite, a file-based database.

Skill for Claude CodeCodex

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 skills/sonichi/sutando/agent-registry
Any agent
npx skills add sonichi/sutando --skill agent-registry
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code, Codex.

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 agent-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/agent-registry.svg)](https://agentmods.dev/skills/sonichi/sutando/agent-registry)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/agent-registry"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/agent-registry.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,092 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 $0.00066 $0.01092
Opus 5 $0.00033 $0.00546
Sonnet 5 $0.00013 $0.00218
Haiku 4.5 $0.00007 $0.00109

Measured 5d ago against content hash 2028192981c9, 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 5d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (hooks/session-start.sh, scripts/_workspace_resolve.py, scripts/registry-client.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agent-registry/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Registry

A thin local service that tracks running agent instances. Claude Code instances register themselves on startup (via a SessionStart hook) and heartbeat while alive; consumers read the live list over a localhost HTTP API.

This is not the AG2 Workforce Hub app. It is a small local service that can optionally mirror its state to an AG2 hub using the hub connection layer (ag2_workforce.hub.client) — see "Optional: AG2 Hub mirroring" below — but the core service has zero third-party dependencies and works entirely offline.

Components

skills/agent-registry/
├── scripts/registry-service.py   # the HTTP service + SQLite store
├── scripts/registry-client.py    # CLI: register / heartbeat / deregister / list / watch
└── hooks/session-start.sh        # Claude Code SessionStart hook
  • DB: <workspace>/data/agent-registry.db (SQLite, auto-created)
  • Discovery file: <workspace>/state/agent-registry.json — written by the service with the bound port so clients find it without a hardcoded port.
  • Port: binds 127.0.0.1, first free port from 7847 upward.

Running the service

It is startable by Sutando three ways, in order of preference:

  1. Auto-start (default). Any registry-client.py call with --autostart launches the service detached if it is not already running. The SessionStart hook passes --autostart, so the first Claude Code session to start brings the registry up.
  2. From startup.sh. For an always-on registry, add to src/startup.sh: python3 skills/agent-registry/scripts/registry-service.py &
  3. By hand: python3 skills/agent-registry/scripts/registry-service.py

Registering Claude Code instances

Add the SessionStart hook to .claude/settings.json:

{
  "hooks": {
    "SessionStart": [
      { "hooks": [
        { "type": "command",
          "command": "bash skills/agent-registry/hooks/session-start.sh" }
      ] }
    ]
  }
}

On session start the hook backgrounds registry-client.py watch, which registers the instance, heartbeats every 30s, and deregisters when the session ends. If it is killed ungracefully the entry ages out via heartbeat staleness (> 90sstale; stopped/stale rows are pruned after 1h).

Read the full file on GitHub · 103 lines

Files

What ships with it

5 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.

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. 5d ago First seen · 103 lines · 66 tokens per session scan A 2028192981c9

Subscribe to this mod's changes

agent-registry is a skill published in the GitHub repository sonichi/sutando (391 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,092 once invoked, about $0.0003 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.