coordinate-external-agents

A guide for coordinating agents that run independently across hosts, sessions, accounts, services, queues, boards, or pull requests.

In plain words
What is it for?
Use it to assign coordinators and write surfaces, record queued or running work, handle blocked or failed tasks, and verify returned changes or artifacts.
Why use it?
It prevents work from disappearing when agents cannot directly message each other by requiring a durable task record, clear ownership, status, and a final report.

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/gaelic-ghost/socket/coordinate-external-agents
Any agent
npx skills add gaelic-ghost/socket --skill coordinate-external-agents
Clone the repo
git clone --depth 1 https://github.com/gaelic-ghost/socket

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 411 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 $0.00051 $0.00411
Opus 5 $0.00026 $0.00205
Sonnet 5 $0.00010 $0.00082
Haiku 4.5 $0.00005 $0.00041

Measured 2d ago against content hash d6635915a5bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coordinate-external-agents 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.

plugins/agent-engineering-skills/skills/coordinate-external-agents/SKILL.md · 41 lines

What it actually says

Coordinate External Agents

Treat an external agent as an independently operated worker, not as a magical subagent. Starting it is not progress unless the coordinator can later discover its state and consume its report.

Workflow

  1. Choose a durable shared surface: task record, issue, pull request, branch, worktree, artifact directory, shared document, queue, or host-native board.
  2. Create a task record with the normal launch envelope plus access, retention, retry/resume, and result-delivery details.
  3. Assign one owner, one coordinator, one artifact/write surface, and one final verification owner. Do not assume direct worker-to-worker messages exist.
  4. Record status using queued, running, blocked, needs-decision, completed, failed, or cancelled; use the selected host's closest equivalent without hiding meaning.
  5. Require a final report on the durable surface and notify the coordinator through the specified return route.
  6. Verify the returned artifact, branch, change, or evidence before treating the task as complete.

Durable Work Rule

Use a queue, board, scheduled task, CI workflow, or service for work that must survive session closure, restart, human input, retry, multiple roles, or later audit. Do not represent a transient child-agent call as durable work.

Boundaries

  • Keep credentials, private context, and mutation authority scoped to the external worker's actual access surface.
  • Use host-specific adapters only for mechanics. This skill owns the universal handoff contract; it does not claim Codex, ChatGPT Work, Hermes, or another host shares one message or task API.
Files

What ships with it

1 file 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. 2d ago First seen · 41 lines · 51 tokens per session scan A d6635915a5bc

Subscribe to this mod's changes

coordinate-external-agents is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 51 tokens to every session and 411 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 2026-08-31.

Related

Other skills, from other repositories

xcode-disk-cleanup

Audit and safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders…

AvdLee/Xcode-Disk-Cleanup-Agent-Skill · 147 tokens

storescreens

Set up and run storescreens-cli to automate App Store screenshot capture for iOS apps: render captioned/framed App Store-ready screenshots with device bezels, markdown captions, and panoramic backgrounds; upload screenshots + per-locale metadata (name, subtitle, description, keywords, what's new, promotional text) to…

ciscoriordan/storescreens-skill · 331 tokens

swift-concurrency-pro

Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.

jacklandrin/OnlySwitch · 35 tokens

swiftui-pro

Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.

jacklandrin/OnlySwitch · 36 tokens

baocut

BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…

JimLiu/baocut · 160 tokens

boutique-swiftui

Integrate Boutique with SwiftUI views using onChange, onStoreDidLoad, bindings, and preview stores. Use when building SwiftUI views that display or react to Boutique-persisted data.

mergesort/Boutique · 45 tokens