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.
git clone --depth 1 https://github.com/KevinZai/commanderWrote 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/commands/kevinzai/commander/ccc-ao)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-ao"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-ao/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.
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-ao"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-ao.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.01146 |
| Opus 5.5 | $0.00014 | $0.00458 |
| Sonnet 5.5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00115 |
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 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-ao — parallel agents in worktrees
CC Commander · /ccc-ao · wraps the ao CLI (@composio/ao) to run parallel agents, each in its own git worktree.
Ask every choice with AskUserQuestion (a plain-text question where it is unavailable): 2 to 4 options, recommended first and marked 🟢. The user's selected model and agent runtime are preserved unless they choose otherwise.
What happens
-
Check the CLI is installed.
command -v ao && ao --versionIf
aois missing, stop and report:ao CLI not installed. Install it with: npm i -g @composio/ao, then run /ccc-ao again.Do not install it yourself. -
Ask what to do:
- 🟢 Spawn agents on this project — choose count, runtime and tasks.
- Spawn from a config file — run a saved
agent-orchestrator.yaml. - Check running agents —
ao status. - Stop agents —
ao stop, after confirmation.
If the user describes something else, handle it with the matching
aosubcommand (ao --help).
Spawn on this project
-
Ask the agent count: 🟢 2 · 3 · 5 · custom.
-
Ask the agent runtime: 🟢 Claude · Codex · Aider · OpenCode.
-
Ask the task strategy:
- 🟢 One task per agent — each agent gets its own task.
- One shared task — all agents work toward one goal.
- Auto-split — the user gives one goal; split it into one task per agent and show the split before spawning.
-
Collect the task text (one per agent, or one goal).
-
Spawn. Confirm the flags with
ao spawn --helpif the command is rejected.ao spawn --agents <n> --model <runtime> --task "<task>" --worktree -
Verify with
ao statusandgit worktree list, then report:ao spawn complete Agents: <n> | Runtime: <runtime> | Worktree: isolated Agent 1: <task> Agent 2: <task>If
ao statusdoes not show the new sessions, report the spawn output verbatim instead of claiming success.
Spawn from a config file
-
Find the config.
ls agent-orchestrator.yaml .ao/config.yaml 2>/dev/null
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 Changed · -23 lines · +23 tokens per session a2d7cbe3071d
- 1mo ago First seen · 151 lines · 12 tokens per session scan A a6593387217f
ccc-ao is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,146 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
commit
Split the changes into atomic commits, preflight and push them. Pass --skip-preflight or --no-push to skip a step.
doc-changelog
Generation and maintenance of the project changelog.
ops-gitflow
Manage the GitFlow branching model: init, feature, release and hotfix branches.
fix-issue
A command that takes a GitHub Issue—a tracked bug, request, or question—and guides its fix from investigation through testing and submission. TDD means writing a failing test first, then changing the code until the test passes.