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-verify)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-verify"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-verify/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-verify"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-verify.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 | $0.00062 | $0.00928 |
| Opus 5.5 | $0.00025 | $0.00371 |
| Sonnet 5.5 | $0.00012 | $0.00186 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
ccc-verify 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 6d 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.
This is a copy
91% identical to verify — 71 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-verify — is this ready for a PR
CC Commander · /ccc-verify · runs the project's real checks in order and reports actual results, not a self-assessment.
Arguments
$ARGUMENTS selects the depth:
| Mode | Checks |
|---|---|
quick |
1 build, 2 types |
full (default) |
1 to 7 |
pre-commit |
2 types, 3 lint, 4 tests on changed files, 5 secrets, 6 debug logs, 7 git status |
pre-pr |
full plus a dependency audit (npm audit --omit=dev, pip-audit, cargo audit or govulncheck ./..., whichever applies and is installed) |
What happens
Find each command in the project first (package.json scripts, Makefile, pyproject.toml, CI workflow files) and prefer it over a generic one. Run the checks in this order:
- Build.
npm run build(orpnpm build/yarn build),cargo build,go build ./...,mvn compile. If it fails, report the errors and stop; later checks are not meaningful on a broken build. - Types.
npx tsc --noEmit,mypy .orpyright, as configured. Report every error aspath:line. - Lint.
npm run lint,npx eslint .,ruff check .,cargo clippy,golangci-lint run, as configured. Report errors and warnings separately. - Tests. The project's test command with coverage (
npm test -- --coverage,pytest --cov,go test -cover ./...,cargo test). Report pass/fail counts and coverage percentage against the project threshold. - Secrets. Scan tracked and staged changes:
gitleaks detect --no-bannerwhen installed, otherwisegit diff HEAD | grep -nE '(api[_-]?key|secret|token|password)\s*[:=]|-----BEGIN [A-Z ]*PRIVATE KEY'. Report file and line only, never the matched value. - Debug logs.
git grep -nE 'console\.log|debugger;' -- ':!*test*' ':!*spec*'for JS/TS (print(for Python,dbg!for Rust). Report locations. - Git status.
git status --shortandgit diff --stat HEADfor uncommitted and modified files.
If a check's tool is not configured, mark it SKIPPED (not configured) rather than passing it.
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.
- 6d ago Changed · +1 lines · +44 tokens per session db70b8c94c65
- 1mo ago First seen · 64 lines · 18 tokens per session scan A 765379d65b94
ccc-verify is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 928 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to verify, differing in 71 lines, and is treated as a copy.
Other commands, from other repositories
work-flow-feature
Complete workflow for developing a new feature, from exploration to merge.
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
fix-tests-execute
Phase 2 of fixing-tests: Fix Execution - investigate, classify, fix, verify, and commit each work item.
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
verify
Run verification commands and confirm output before making success claims. Use before committing, creating PRs, or claiming work is complete. Evidence before assertions, ALWAYS.