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-buildnpx skills add KevinZai/commander --skill ccc-buildgit 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-build)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-build"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-build.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 | $0.00045 | $0.02509 |
| Opus 5 | $0.00023 | $0.01255 |
| Sonnet 5 | $0.00009 | $0.00502 |
| Haiku 4.5 | $0.00005 | $0.00251 |
Grade A, and why
ccc-build 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 4d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-build — Scaffold a project
Click-first build flow. Four templates, one spec interview, one background agent. User clicks a tile, answers 3 questions, walks away — the scaffold lands in their worktree while they wait.
Response shape (EVERY time)
Output exactly these three sections in order:
1. Brand header (one line, markdown)
**CC Commander** · $ccc-build · Scaffold a project or feature
2. Context strip (one paragraph)
Detect target location with three quick reads (parallel Bash, silent on failure):
git rev-parse --abbrev-ref HEAD→ branchls -1 | head -20→ repo inventory (empty repo? existing project?)test -f package.json && cat package.json | head -5→ detect existing stack
Render one line:
🧭 Target:
<cwd basename>· branch:<branch>· <empty repo | Node project | Python project | other>
If an existing project is detected, add a gentle note: "I'll scaffold into a sub-directory so I don't clobber your current code."
3. The picker — AskUserQuestion with 4 templates
Read ${CLAUDE_PLUGIN_ROOT}/menus/ccc-build.json for canonical option data. Surface exactly 4 of the 5 non-back choices (drop "mobile" if the user's stack is backend-only; otherwise keep web-app / api / cli / mobile).
question: "What are we building?"
header: "CC Commander Build"
multiSelect: false
options:
- label: "🌐 Web app"
description: "Next.js + Tailwind + shadcn/ui — SSR, auth, Stripe-ready."
preview: "Best for: product sites, dashboards, SaaS frontends. 3-question spec → 2-4 min scaffold."
- label: "🔌 API / backend"
description: "TypeScript Fastify or Hono, Postgres via Supabase, zero-boilerplate."
preview: "Best for: REST or GraphQL backends, webhook handlers, internal services."
- label: "⌨️ CLI tool"
description: "Node + commander, figlet banner, test scaffold, publish-ready."
preview: "Best for: dev tooling, scripts, publish-to-npm utilities."
- label: "📝 From a spec"
description: "Describe the idea in plain English — spec interview → plan → build."
preview: "Best for: anything that doesn't fit a template. Routes through ccc-plan first."
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 198 lines · 45 tokens per session scan A 2655e4b47b83
ccc-build is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,509 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
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
mobile-design
Evaluation criteria for grading rendered mobile UI screens. Use when reviewing, critiquing, or self-checking a mobile UI screenshot — especially after any UI edit in an agentic loop — to decide pass/fail and produce concrete fixes. Targets Compose Multiplatform (Android + iOS), Material 3. The mobile counterpart to…
writing-java-kotlin
Idiomatic modern Java and Kotlin JVM development. Use when writing .java, .kt, or .kts code; changing Gradle or Maven builds; or working on Spring, Micronaut, Quarkus, Ktor, Android JVM modules, JUnit, Mockito, Kotest, ktlint, detekt, or JVM CLI/services. Emphasizes JDK toolchains, null-safety, fast focused…
rn-asset-hygiene
Use when a React Native project has messy assets — unreferenced/unused image, SVG, or Lottie files, scattered or deeply-relative require() paths, or string-based asset references you want made type-safe. Audits first (read-only), then offers git-safe cleanup. Wraps the rn-typed-assets CLI.
rn-newarch-audit
Use when planning a React Native upgrade or asking "is my app ready for the New Architecture?" — audits which dependencies and app-local native modules block enabling the New Architecture. Read-only; reports and interprets, changes nothing. Wraps the rn-newarch-ready CLI.
rn-metro-console
Use when you need to read a running React Native app's console output — confirm a log fired, watch console.warn/error, or verify runtime behavior — without opening the DevTools GUI. Reads logs from Metro's CDP endpoint; bounded by default. Read-only with respect to project source. Runs the bundled rn-console.mjs…