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 skills/kevinzai/commander/ccc-onboardnpx skills add KevinZai/commander --skill ccc-onboardgit 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/skills/kevinzai/commander/ccc-onboard)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-onboard"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-onboard.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 5.1 | $0.00032 | $0.01933 |
| Opus 5 | $0.00016 | $0.00966 |
| Sonnet 5 | $0.00006 | $0.00387 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
ccc-onboard 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-onboard — New Contributor Onboarding
CC Commander · $ccc-onboard · Role → first task → first hour
Use this when a contributor is new to the repository and needs a practical first hour, not a generic tour. Build the guide from the repo’s own instructions and scripts.
Response Shape
Always return these sections:
- Brand header:
**CC Commander** · $ccc-onboard · Contributor first hour
- Repo context:
Read only the files that exist:
CLAUDE.mdfor local conventions, required tools, test commands, and workflow rulesBIBLE.mdfor product architecture, domain language, and non-negotiable project rulespackage.jsonfor scripts, package manager clues, and workspace structureREADME.mdonly if the first three do not provide enough starter links
Summarize:
Repo: <name> · package manager: <npm|bun|pnpm|yarn|unknown> · scripts: <top useful scripts> · primary stack: <detected stack>
- Role picker —
AskUserQuestion
Never show more than four options in one picker. The first picker covers the three most common code roles plus a "More roles" option; the second picker covers docs and first-PR onboarding.
question: "What kind of contributor are you onboarding?"
header: "CC Commander Onboard"
multiSelect: false
autocomplete: true
options:
- label: "Frontend"
value: "frontend"
description: "UI, components, client flows, accessibility, and visual polish."
preview: "First task focuses on finding a small UI improvement and validating it locally."
- label: "Backend"
value: "backend"
description: "APIs, services, persistence, auth, jobs, and platform integrations."
preview: "First task focuses on one safe server-side fix with tests."
- label: "Full-stack"
value: "full-stack"
description: "End-to-end product change crossing UI and backend."
preview: "First task traces one user flow from UI to data boundary."
- label: "More roles"
value: "more-roles"
description: "Docs or smallest safe first PR."
preview: "Opens a second picker for non-code or first-contribution paths."
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 First seen · 223 lines · 32 tokens per session scan A d9a830a2cbf0
ccc-onboard is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,933 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 2026-08-31.
Other skills, from other repositories
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
verify-gates
Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…
agency-roster
Use when a round references agency-agents catalogs, role-family routing, multi-agent identity prompts, or English/Chinese specialist role catalogs.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.