ccc-ao

ccc-ao is a command for coding agents from KevinZai/commander. It costs 12 tokens per session (890 once invoked), scanned A, original, MIT.

A command-line tool for starting multiple coding agents on separate Git worktrees, which are isolated copies of a project. Agents can work in parallel on shared or separate tasks.

In plain words
What is it for?
Use it to start, monitor, and stop parallel agents, choose their models, and assign work from the current project or a configuration file.
Why use it?
It helps divide larger jobs among agents without having their file changes collide.

Command

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 commands/kevinzai/commander/ccc-ao
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

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 ccc-ao

README.md
[![agentmods](https://agentmods.dev/badge/commands/kevinzai/commander/ccc-ao.svg)](https://agentmods.dev/commands/kevinzai/commander/ccc-ao)
Your own site
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-ao"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-ao.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 890 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 $0.00012 $0.00890
Opus 5 $0.00006 $0.00445
Sonnet 5 $0.00002 $0.00178
Haiku 4.5 $0.00001 $0.00089

Measured yesterday against content hash a6593387217f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccc-ao 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 yesterday.

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.

commands/ccc-ao.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ao — Composio Agent Orchestrator

Wraps the ao CLI (@composio/ao). Spawns parallel agents across projects with git worktree isolation.

When activated:

Check if ao CLI is available:

which ao

If not found, display:

ao CLI not installed.
Run: npm i -g @composio/ao
Then re-invoke /ao once installed.

If found, check the version:

ao --version

Then present via AskUserQuestion:

Option What it does
Spawn agents on current project (Recommended) Ask: how many, what tasks, model selection
Spawn from config file Read agent-orchestrator.yaml, show configured projects
Check running agents Run ao status — show active sessions
Stop agents Run ao stop — kill running sessions
Something else Free text

Spawn Flow

When user picks "Spawn agents on current project":

  1. Ask number of agents via AskUserQuestion:

    • 2 agents
    • 3 agents
    • 5 agents
    • Custom number
  2. Ask model via AskUserQuestion:

    • Claude (Recommended)
    • Codex
    • Aider
    • OpenCode
  3. Ask task assignment strategy via AskUserQuestion:

    • One shared task (agents collaborate on the same goal)
    • One task per agent (assign a separate task to each agent)
    • Auto-split from description (describe overall goal, split automatically)
  4. Collect task(s) — one per agent if individual, or one overall goal if auto-split.

  5. Run the spawn command:

    ao spawn --agents [n] --model [model] --task "[task]" --worktree
    
  6. Show spawned summary:

    ao spawn complete
    Agents: [n] | Model: [model] | Worktree: isolated
    Task(s):
      Agent 1: [task]
      Agent 2: [task]
      ...
    

Spawn from Config File

When user picks "Spawn from config file":

  1. Check for config:

    ls agent-orchestrator.yaml 2>/dev/null || ls .ao/config.yaml 2>/dev/null
    
  2. If found, read and display the configured projects and agents.

  3. Ask which project/config to run via AskUserQuestion.

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 12 tokens per session scan A a6593387217f

Subscribe to this mod's changes

ccc-ao is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 890 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 2026-09-03.