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-refactor-clean)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-refactor-clean"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-refactor-clean/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-refactor-clean"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-refactor-clean.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 | $0.00043 | $0.01230 |
| Opus 5.5 | $0.00017 | $0.00492 |
| Sonnet 5.5 | $0.00009 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
ccc-refactor-clean 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.
This is a copy
89% identical to refactor-clean — 135 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-refactor-clean — remove dead code under test
CC Commander · /ccc-refactor-clean · detects dead code, sorts it by risk, deletes the safe items one at a time with a green test run after each, and reports what was removed.
Arguments
$ARGUMENTS: optional path to limit the scan. Default: the repository root.
What happens
-
Check the starting state.
git status --porcelainA revert in step 5 restores files from
HEAD, which would discard uncommitted edits. If the tree is dirty, ask with AskUserQuestion (Codex: plain-text question):- 🟢 Stop so I can commit first — nothing is changed.
- Continue on clean files only — files with uncommitted changes are excluded from deletion.
-
Name the test command and establish a baseline. Use the project's own script first (
npm test,pnpm test,pytest,go test ./...,cargo test, or theMakefile/justfiletarget). Run it. If the baseline is not green, report the failures and stop; dead-code removal needs a passing suite to prove anything. -
Detect dead code with the tools that fit the stack and are available (run through
npxonly when the project already uses npm):Tool Finds Command knip Unused exports, files, dependencies npx knipdepcheck Unused npm dependencies npx depcheckts-prune Unused TypeScript exports npx ts-prunevulture Unused Python code vulture <src>deadcode Unused Go code deadcode ./...cargo-udeps Unused Rust dependencies cargo +nightly udepsIf no tool is available, find exported names and count their references:
rg --no-filename -o -r '$1' '^export (?:const|function|class|type|interface) (\w+)' <path> | sort -u rg -n --fixed-strings '<name>' --glob '!<defining-file>' <path>A name with zero references outside its defining file is a candidate.
-
Categorize every finding:
Tier Examples Action SAFE Unused utilities, test helpers, internal functions Delete in the loop below CAUTION Components, API routes, middleware Run the CAUTION checks in step 6 first DANGER Config files, entry points, type definitions, public package API Report only; do not delete
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 · +13 lines · +29 tokens per session 4bd808bfa585
- 1mo ago First seen · 85 lines · 14 tokens per session scan A faf32cd5e23a
ccc-refactor-clean is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,230 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to refactor-clean, differing in 135 lines, and is treated as a copy.
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.
work-flow-bugfix
Complete workflow to fix a bug, from diagnosis to deployment.
dev-debug
Methodical and systematic bug diagnostic and resolution.
planning-triage
Quick-score an enhancement, bug, or feedback item using the impact-first triage framework. Creates an issue if approved.
p6-bugfix
Fixes bugs and vulnerabilities found during the QA phase (functional tests, exploratory tests, accessibility check, security audit, pentest). Each fix is secured by a regression test.