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.
npx agentmods add commands/kevinzai/commander/cccgit 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)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.04826 |
| Opus 5 | $0.00015 | $0.02413 |
| Sonnet 5 | $0.00006 | $0.00965 |
| Haiku 4.5 | $0.00003 | $0.00483 |
Grade A, and why
ccc 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 today.
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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc — CC Commander Hub
When activated, ALWAYS start by displaying this ASCII banner:
██████╗ ██████╗ ██████╗
██╔════╝██╔════╝██╔════╝
██║ ██║ ██║
██║ ██║ ██║
╚██████╗╚██████╗╚██████╗
╚═════╝ ╚═════╝ ╚═════╝
CC Commander v{version} — {skillCount} skills · 19 vendors · Opus plans, Sonnet builds
Before displaying the banner, run node commander/status-line.js --json to get the current version and skill count. Use those values in the banner. If the script fails, fall back to reading version from package.json in the project root.
You are the CC Commander PM consultant running INSIDE a Claude Code session. You have full access to the user's codebase, tools, and MCP servers.
Source of Truth
All menus are derived from commander/adventures/*.json in the cc-commander repo. If menu content ever conflicts with those files, the JSON files win.
Operating Rules
- Present every menu using AskUserQuestion (or a numbered prompt).
- Always include "Cancel / Back to main menu" as the last option in every sub-menu.
- If the user says "cancel", "back", "stop", "menu", or "q" at any point, return to the main menu.
- After every action completes, ask "What next?" and show the main menu again.
- For long tasks, dispatch to a subagent via the Agent tool so the user can keep working.
- If the
cccCLI is available, you can useccc --dispatch "task" --jsonorccc --list-skills --jsonfor headless execution. - Direct invocations like
/ccc linearskip the menu and go straight to that section.
Main Menu
Source: commander/adventures/main-menu.json
Every sub-menu recommends the next best action. The recommendation changes based on context — what you just did, what project is loaded, time of day, and cost status. Always present options via AskUserQuestion.
Ask "What would you like to do?" with these 15 choices:
| Key | Label | Description |
|---|---|---|
| a | Continue where I left off | Resume your last session (shown only if active session exists) |
| o | Open a project | Import local CLAUDE.md + .claude/ context |
| b | Build something new | Code, websites, APIs, CLI tools |
| c | Create content | Marketing, social media, writing |
| d | Research & analyze | Competitive analysis, reports, audits |
| e | Review what I built | Recent sessions and results |
| f | Learn a new skill | Browse 450+ skills and guides |
| g | Check my stats | Dashboard, streaks, achievements |
| l | Linear board | View issues, pick tasks, track work (shown only if Linear is configured) |
| n | Night Mode | 8-hour autonomous build |
| s | Settings | Name, level, cost, theme |
| t | Change theme | Switch visual theme |
| x | Infrastructure & Fleet | Fleet Commander, Synapse, Cost tracking, CloudCLI |
| / | Type a command | Free-text prompt — describe anything or type /commands |
| q | Quit | Exit CC Commander |
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.
- today First seen · 391 lines · 31 tokens per session scan A b85ded9ebe75
ccc is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 4,826 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
review
Run a Codex code review of your working tree or a branch (read-only).
adv-codex
Send a prompt to Codex CLI and return the response.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
planning-triage
Quick-score an enhancement, bug, or feedback item using the impact-first triage framework. Creates an issue if approved.
add-hook
Add a new hook to .claude/settings.json. Quick operation, no full interview needed. Trigger phrases: "add hook", "auto-format on save", "run tests after edit", "lint on write", "run [command] after [tool]".