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-devfleet)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-devfleet"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-devfleet/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-devfleet"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-devfleet.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 | $0.00040 | $0.01107 |
| Opus 5.5 | $0.00016 | $0.00443 |
| Sonnet 5.5 | $0.00008 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
ccc-devfleet 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 5d 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.
This is a copy
94% identical to devfleet — 120 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-devfleet — parallel agents via DevFleet
CC Commander · /ccc-devfleet · a mission DAG from a plain-language brief, run by parallel agents in their own git worktrees.
DevFleet is an opt-in third-party MCP server, absent by default. Its tools appear as mcp__devfleet__*. If they are not exposed in this session, say so, give the install line from DevFleet's own docs (its default is claude mcp add devfleet --transport http http://localhost:18801/mcp), and offer /ccc-fleet or the Agent tool with isolation: worktree as the built-in alternative.
Flow
brief -> plan_project -> show plan -> user approves
-> dispatch_mission(first) -> agent works in its worktree -> auto-merge
-> dependents auto-dispatch -> ... -> get_report(each) -> summary
What happens
-
Plan the project from the user's brief:
mcp__devfleet__plan_project(prompt="<user's description>")Show the project name and id, each mission's title, type and id, and the dependency DAG (which missions block which).
-
Ask with AskUserQuestion (Codex: a plain-text question) before anything runs, unless the user already said to go ahead:
- 🟢 Dispatch the plan — starts the first mission; dependents follow automatically
- Edit the plan — adjust missions with
create_mission/cancel_mission, then show it again - Cancel — nothing is dispatched
-
Dispatch the mission with an empty
depends_on:mcp__devfleet__dispatch_mission(mission_id="<first_mission_id>")Missions from
plan_projectcarryauto_dispatch=true, so the rest start as their dependencies finish. Missions added by hand withcreate_missionneedauto_dispatch=trueset explicitly for the same behavior. -
Monitor progress:
mcp__devfleet__get_dashboard() mcp__devfleet__get_mission_status(mission_id="<id>")Poll
get_mission_statusfor long missions so the user sees progress; usewait_for_missiononly for short ones. Report mission titles and ids with each status.
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.
- 5d ago Changed · +5 lines · +9 tokens per session 60895dc2370e
- 1mo ago First seen · 93 lines · 31 tokens per session scan A b1ad42c54f16
ccc-devfleet is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,107 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to devfleet, differing in 120 lines, and is treated as a copy.
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.