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.
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.
npx skills add awslabs/cli-agent-orchestrator --skill cao-supervisor-protocolsgit clone --depth 1 https://github.com/awslabs/cli-agent-orchestratorWrote 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.
[](https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-supervisor-protocols)<a href="https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-supervisor-protocols"><img src="https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-supervisor-protocols.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00962 |
| Opus 5 | $0.00013 | $0.00481 |
| Sonnet 5 | $0.00005 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
cao-supervisor-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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CAO Supervisor Protocols
Use this skill when supervising worker agents through CLI Agent Orchestrator.
This skill covers how supervisors should dispatch work, decide between assign and handoff, and receive worker results without blocking inbox delivery.
Core MCP Tools
From cao-mcp-server, supervisors orchestrate work with:
assign(agent_profile, message)for asynchronous work that returns immediatelyhandoff(agent_profile, message)for synchronous work that blocks until the worker finishessend_message(message, receiver_id=None)for direct messages —receiver_iddefaults to the terminal that created yours via handoff/assignanswer_user_prompt(terminal_id, answer)for answering a Hermes worker that reportswaiting_user_answer
Your own terminal ID is available in the CAO_TERMINAL_ID environment variable. CAO appends it to assigned task messages and records it on worker terminals automatically, so you rarely need to handle it yourself.
Choosing Between Assign and Handoff
Use assign when the worker should continue independently and report back later. This is the normal pattern for fan-out work or parallel execution.
Use handoff when the next step is blocked on the worker result. The orchestrator waits for completion, captures the worker output, and returns it directly to the supervisor.
Typical pattern:
- Use
assignfor analysis, research, or code changes that can run in parallel. - Use
handofffor report generation, blocking review steps, or any task where you need the result before you can continue.
Idle-Based Message Delivery
Assigned workers usually return results through send_message. Those inbox messages are delivered to the supervisor automatically when the supervisor terminal becomes idle.
This means supervisors should:
- Dispatch all planned worker tasks first
- Finish the turn after dispatching work
- Avoid running placeholder shell commands just to wait
Do not keep the terminal busy with sleep, echo, or similar commands while waiting. A busy terminal delays inbox delivery.
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.
- 8d ago First seen · 91 lines · 25 tokens per session scan A 27fea276b2c5
cao-supervisor-protocols is a skill published in the GitHub repository awslabs/cli-agent-orchestrator (1,223 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 962 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.
Other skills, from other repositories
coordination
Use when orchestrating complex or multi-lane work, decomposing tasks across peers, choosing status/board surfaces, running mesh roundups, or keeping high-level progress visible.
mindforge-swarm-execution
Use when executing implementation plans with independent tasks in the current session.
mindforge-thread
Manage persistent context threads for cross-session work.
mindforge-add-backlog
Add an idea to the backlog parking lot (999.x numbering).
mindforge-review-backlog
Review and promote backlog items to active milestone.
mindforge-execute-phase_extended
Use when you have a written implementation plan to execute in a separate session with review checkpoints.