cao-worker-protocols

cao-worker-protocols is a skill for Claude Code, Codex from awslabs/cli-agent-orchestrator. It costs 21 tokens per session (641 once invoked), scanned A, original, Apache-2.0.

Rules for an agent worker receiving tasks from CAO, the CLI Agent Orchestrator, including how to finish assigned work and report results.

In plain words
What is it for?
It helps worker agents distinguish blocking handoffs from non-blocking assignments and return results through the expected channel.
Why use it?
It prevents workers from using the wrong completion or messaging method when work is assigned directly or handed off by another agent.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit It helps worker agents distinguish blocking handoffs from non-blocking assignments and return…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/awslabs/cli-agent-orchestrator/cao-worker-protocols
About the project

CLI Agent Orchestrator is a tool that coordinates multiple AI coding command-line programs by running them as separate workers in isolated terminal sessions. A supervisor uses it to delegate software tasks to specialist agents in parallel or in sequence while the workers retain their normal command-line capabilities. The catalogue skills operate this orchestration workflow.

awslabs/cli-agent-orchestrator · 1,213 stars · on GitHub · awslabs.github.io

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 awslabs/cli-agent-orchestrator --skill cao-worker-protocols
Clone the repo
git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator

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 cao-worker-protocols

README.md
[![agentmods](https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-worker-protocols.svg)](https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-worker-protocols)
Your own site
<a href="https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-worker-protocols"><img src="https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-worker-protocols.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00641
Opus 5 $0.00010 $0.00320
Sonnet 5 $0.00004 $0.00128
Haiku 4.5 $0.00002 $0.00064

Measured 7d ago against content hash 00df779ac8aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cao-worker-protocols 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 7d 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/cao-worker-protocols/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CAO Worker Protocols

Use this skill when acting as a worker agent inside CLI Agent Orchestrator.

This skill explains how workers should interpret assigned versus handed-off work, when to call send_message, and how to report results back cleanly.

Understand the Dispatch Mode

Workers receive tasks through one of two orchestration modes:

  • handoff: blocking work where the orchestrator captures your final output automatically
  • assign: non-blocking work where you must actively return results to the requesting terminal

Depending on provider and CAO behavior, a handoff may be made explicit in the task text. For example, Codex workers currently receive a [CAO Handoff] prefix for blocking handoffs. Other providers may rely on the task wording and orchestration context instead.

Rules for Handoff Tasks

When the task is a blocking handoff, complete the work and present the result in your normal response. The orchestrator captures that response automatically.

Do not call send_message for ordinary handoff completion unless the task explicitly asks for additional side-channel communication.

Rules for Assigned Tasks

When the task came through assign, send your results back after you finish the work:

  1. Format the result clearly and concisely.
  2. Call send_message(message=...) — omitting receiver_id routes the result to the terminal that assigned the task (the recorded caller). This is the reliable default.
  3. If the task message names a different callback terminal (directly or in an appended suffix such as [Assigned by terminal ...]), pass that ID as receiver_id instead.

Do not stop after writing a normal response if the assignment explicitly requires a callback. The requesting terminal depends on send_message to receive the result.

Your own CAO_TERMINAL_ID identifies your terminal, not the callback target. Never pass it as receiver_id.

Message Formatting

Return results that are easy for the supervisor to merge into a larger workflow:

Read the full file on GitHub · 59 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. 7d ago First seen · 59 lines · 21 tokens per session scan A 00df779ac8aa

Subscribe to this mod's changes

cao-worker-protocols is a skill published in the GitHub repository awslabs/cli-agent-orchestrator (1,213 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 641 once invoked, about $0.0001 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.