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-audit)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-audit"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-audit/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-audit"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-audit.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 | $0.00045 | $0.00966 |
| Opus 5.5 | $0.00018 | $0.00386 |
| Sonnet 5.5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
ccc-audit 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-audit — project health audit
CC Commander · /ccc-audit · one read-only pass over dependencies, build output, types, dead code, secrets, env vars and project instructions, ending in a scored report.
Arguments
$ARGUMENTS (optional) narrows the run:
| Argument | Checks run |
|---|---|
| (none) | all seven |
security |
1 dependencies, 5 secrets, 6 env vars |
deps |
1 dependencies, 4 dead code |
perf |
2 bundle size |
What happens
Detect the package manager from the lockfile (pnpm-lock.yaml → pnpm, yarn.lock → yarn, bun.lockb → bun, otherwise npm). Run each check, record the actual output, and mark a check skipped with the reason when its tool or input is absent.
-
Dependencies. Look for high and critical advisories.
npm audit --json # or: pnpm audit --json | yarn npm audit --json -
Bundle size. Use existing build output (
dist/,build/,.next/,out/); if none exists, run the project'sbuildscript once. Flag any file over 500 KB.find dist build .next/static out -type f \( -name '*.js' -o -name '*.css' \) -size +500k -exec ls -lh {} \; 2>/dev/null -
TypeScript. Zero errors required. Skip when there is no
tsconfig.json.npx tsc --noEmit -
Dead code. Find unused exports and unreferenced files with an installed tool (
npx knipornpx ts-prune). Without one, reportskipped: no dead-code tool installedrather than guessing. -
Secrets. Scan tracked files for hardcoded keys, tokens and passwords. Report
path:lineand the kind of secret; never print the value.git grep -nIE '(api[_-]?key|secret|token|passw(or)?d)[^=:]{0,20}[=:][[:space:]]*["'"'"'][^"'"'"']{12,}|AKIA[0-9A-Z]{16}|sk-[A-Za-z0-9_-]{20,}|-----BEGIN [A-Z ]*PRIVATE KEY' -- ':!*.lock' ':!*lock.json' -
Env vars. Compare the variables the code reads with the documented ones in
.env.example(or the README). Report each undocumented or unused variable by name only.
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 · +57 lines · +24 tokens per session eb1aeac4f064
- 1mo ago First seen · 25 lines · 21 tokens per session scan A ba6a9bee43a1
ccc-audit is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 966 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 2026-09-03.
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.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
deps-update
Audit and update dependencies safely.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
dev-flutter
Create Flutter widgets, screens and features with Clean Architecture.
work-quick
Quick workflow for trivial changes (1-3 files, < 50 lines, zero risk).