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-spawn)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-spawn"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-spawn/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-spawn"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-spawn.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 | $0.00055 | $0.02734 |
| Opus 5.5 | $0.00022 | $0.01094 |
| Sonnet 5.5 | $0.00011 | $0.00547 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade A, and why
ccc-spawn 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-spawn — parallel peers with clear boundaries
CC Commander · /ccc-spawn · a reviewed spawn plan, ready-to-run peer commands, and a status view of the peers you launched.
Before you spawn
- Peer messaging uses the claude-peers MCP server (
list_peers,send_message,check_messages,set_summary). It is opt-in and absent by default. Without it, peers still run, butstatusandkillfall back togit worktree listand the user closing terminals; say so once. - For parallel work inside this session, the built-in route is usually simpler: the Agent tool with
isolation: worktreefor a few bounded tasks, the Workflow tool for scripted fan-out, or/ccc-fleet. Offer it when the user has not asked for separate sessions. - Codex: launch peers with
codex exec --json --cd <worktree> "<prompt>"instead ofclaude -p. - Peers inherit the user's selected model. Add
--model <alias>(fable,opus,sonnet,haiku) only when the user chooses one for a role. - Never quote a dollar estimate without a source. Describe cost as relative (one peer ≈ one session of that size) and point to
/ccc-costfor actuals.
Routing
Parse $ARGUMENTS:
| Form | Flow |
|---|---|
| empty | Menu |
quick <task> |
Quick: one self-contained peer |
team <n> <role1> <role2> … |
Team: n peers with assigned roles |
swarm <goal> |
Swarm: decompose the goal into a peer team |
expert <domain> |
Expert: one domain review peer |
status |
Status of active peers and messages |
templates |
Pre-built team compositions |
kill |
Ask every spawned peer to finish and exit |
Menu
With no arguments, ask with AskUserQuestion (Codex: a plain-text question):
- 🟢 Quick — one fire-and-forget peer for a self-contained task
- Team or swarm — several peers; you name the roles, or the goal is decomposed for you
- Expert review — one domain expert reviews files you choose
- Manage — status, templates, or stop peers
For Team or swarm, ask next: 🟢 Swarm (decompose my goal) · Team (I name the roles) · Template (start from a pre-built team). For Manage, ask: 🟢 Status · Templates · Kill.
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 · -96 lines · +43 tokens per session bf73bb129f4e
- 1mo ago First seen · 302 lines · 12 tokens per session scan A 7613adef657a
ccc-spawn is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,734 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
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
sync
Reconcile coco tracker state with the configured issue tracker. Syncs task statuses and reports mismatches.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.