What is agent-coordination?

A skill for coordinating multiple coding agents through a shared registry and inbox. Agents can register their abilities, find available agents, send structured messages, and pass work to one another.

Registering agents, matching work to capabilities, sending updates or requests, checking unread messages, and handing over project tasks.

It prevents coordination from relying on informal messages by recording who can do a task and what requests or handoffs are waiting.

agent-coordination — Skill for Claude Code and Codex by fthsrbst/mnema

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.

Any agent

npx skills add fthsrbst/mnema --skill agent-coordination

Clone the repo

git clone --depth 1 https://github.com/fthsrbst/mnema

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fthsrbst/mnema/agent-coordination/github.svg)](https://agentmods.dev/skills/fthsrbst/mnema/agent-coordination)

Your own site

<a href="https://agentmods.dev/skills/fthsrbst/mnema/agent-coordination"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/agent-coordination/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fthsrbst/mnema/agent-coordination"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/agent-coordination.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 885 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.00885
Opus 5.5	$0.00018	$0.00354
Sonnet 5.5	$0.00009	$0.00177
Haiku 4.5	$0.00004	$0.00089

Measured 1mo ago against content hash 451d99215671, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-coordination 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 1mo 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.

skills/agent-coordination/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Koordinasyonu

Hub, agent'ların birbirini bulması, iletişim kurması ve iş devretmesi için altyapı sağlar.

Yetenek Kaydı (Capability Registry)

Her agent kendi yeteneklerini kaydeder:

agent_register

{
  "agent": "claude-code",
  "machine": "fatih-pc",
  "capabilities": ["code_review", "testing", "refactoring", "documentation"],
  "models": ["claude-sonnet-4-20250514"],
  "max_concurrent": 2
}

agent_find

İş için uygun agent bulmak:

{ "capability": "testing", "project": "my-project" }

Yeteneğe göre eşleşen, available durumundaki agent'ları döner

agent_heartbeat

Uzun süren işlerde canlılık sinyali:

{ "uid": "agent-uid" }

60 dakika heartbeat gelmezse agent offline işaretlenir

Mesajlaşma

agent_message_send

{
  "from_agent": "claude-code",
  "to_agent": "cursor-agent",
  "project": "my-project",
  "kind": "request",
  "subject": "API test'i gerekli",
  "body": "Yeni endpoint'ler eklendi, smoke test rica ediyorum"
}

Mesaj türleri (kind):

info — bilgilendirme
request — istek/rica
response — yanıt
handoff — iş devri (payload ile bağlam taşır)
alert — acil uyarı

agent_inbox

Okunmamış mesajları almak:

{ "agent": "cursor-agent", "limit": 10 }

agent_message_read

Mesajı okundu işaretle:

{ "uid": "message-uid" }

Structured Handoff (İş Devri)

Bir agent'tan diğerine tam bağlam devri:

agent_handoff

{
  "from_agent": "claude-code",
  "to_agent": "cursor-agent",
  "project": "my-project",
  "notes": "Auth modülünde kaldım, token refresh mantığı eksik"
}

Handoff paketi şunları içerir:

Proje map'i (mimari, modüller, komutlar)
Son 3 oturum özeti
Aktif görevler
Agent presence (kim çalışıyor)
İlgili hafızalar

Ne zaman handoff:

Oturum kapanıyor ama iş bitmedi
Başka agent'ın uzmanlığı gerekli
Uzun süreli iş devri

Inbox Kontrol Zamanları

Durum	Aksiyon
Oturum başı	`agent_inbox` kontrol et
Görev claim öncesi	İlgili mesaj var mı bak
Uzun iş ortası	Periyodik inbox kontrolü
Handoff sonrası	Mutlaka inbox'ı oku

Read the full file on GitHub · 115 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.

1mo ago First seen · 115 lines · 44 tokens per session scan A 451d99215671

Subscribe to this mod's changes

agent-coordination is a skill published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 885 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Building agents ai-agents claude cli codex local-first mcp

zootopia-ppt

A presentation-making workflow that turns a speech or slide content into images showing an animated world of human-like animals. It first plans each slide and then generates the slide images.

jin-bo/agentao · 152 tokens

kanban-tasks

A task-board workflow for breaking work into cards and moving them through stages such as inbox, ready, doing, review, and done. It also includes a background service and a web interface for the board.

jin-bo/agentao · 221 tokens

ocr

OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or screenshot, or recognize characters in an image file (.jpg, .jpeg, .png, .gif, .webp). Requires QWENAPIKEY and…

jin-bo/agentao · 99 tokens

agent-coordination