Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KevinZai/commandernpx agentmods add commands/kevinzai/commander/ccc-orchestrateWrote 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-orchestrate)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-orchestrate"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-orchestrate/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-orchestrate"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-orchestrate.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 | $0.00053 | $0.01731 |
| Opus 5.5 | $0.00021 | $0.00692 |
| Sonnet 5.5 | $0.00011 | $0.00346 |
| Haiku 4.5 | $0.00005 | $0.00173 |
Grade A, and why
ccc-orchestrate 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 6d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-orchestrate — chained agent workflows
CC Commander · /ccc-orchestrate · runs agents in sequence, each reading the previous handoff, and ends with one report.
Usage
/ccc-orchestrate <workflow> "<task description>"
/ccc-orchestrate custom "<agent,agent,...>" "<task description>"
$ARGUMENTS:
| Argument | Chain |
|---|---|
feature <description> |
planner → tdd-guide → code-reviewer → security-reviewer |
bugfix <description> |
planner → tdd-guide → code-reviewer |
refactor <description> |
architect → code-reviewer → tdd-guide |
security <description> |
security-reviewer → code-reviewer → architect |
custom <agents> <description> |
the comma-separated agents, in order |
The stage agents resolve, in order, to a project agent in .claude/agents/<name>.md, a personal agent in ~/.claude/agents/<name>.md, or the Commander plugin agents (commander:product-manager for planner, commander:qa-engineer for tdd-guide, commander:reviewer for code-reviewer, commander:security-auditor for security-reviewer, commander:architect for architect). The Agent tool lists the subagent types available in this session. If $ARGUMENTS names no workflow, ask with AskUserQuestion:
- 🟢 feature — full plan, test-first build, quality and security review.
- bugfix — plan, test-first fix, review.
- refactor — design first, then review and tests.
- security — security-led review.
What happens
-
Confirm each agent in the chain exists:
ls .claude/agents/<name>.md ~/.claude/agents/<name>.md 2>/dev/nullWhen neither file exists, use the Commander plugin agent mapped above if the Agent tool lists it; otherwise run the stage as
general-purposewith the stage's instructions inline and say so in the handoff. Never stop for a missing agent file. -
For each agent in order, call the Agent tool with the task, the previous handoff (none for the first), and the files in scope. Keep the user's selected model unless they choose otherwise; set Agent
efforttohighfor planner, architect and security-reviewer stages. Give implementing stagesisolation: worktreewhen they write code in parallel with other work.
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.
- 6d ago Changed · -53 lines · +39 tokens per session a806d0e4f86a
- 1mo ago First seen · 232 lines · 14 tokens per session scan A de6e70db0fe9
ccc-orchestrate is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,731 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.