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-harness-audit)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-harness-audit"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-harness-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-harness-audit"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-harness-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 | $0.00047 | $0.00778 |
| Opus 5.5 | $0.00019 | $0.00311 |
| Sonnet 5.5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
ccc-harness-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 14d 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
94% identical to harness-audit — 93 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-harness-audit — deterministic setup scorecard
CC Commander · /ccc-harness-audit · a reproducible score per category, failing checks with file paths, and the top three fixes.
Arguments
$ARGUMENTS:
- scope (optional):
repo(default),hooks,skills,commands,agents --format text|json(optional;textdefault,jsonfor automation)
What happens
-
Locate the audit engine, first match wins:
scripts/harness-audit.jsin the current repository (an everything-claude-code checkout audits itself)vendor/everything-claude-code/scripts/harness-audit.jsin a CC Commander checkout
If neither exists, ask the user for the path to a checkout that has it. Without the script, stop and say the audit cannot run; never produce a manual score.
-
Run it against the current project:
node <engine path> <scope> --format <text|json> --root "$PWD"The script auto-detects whether the root is the everything-claude-code repo or a consumer project. On a non-zero exit, show stderr and stop.
-
The script is the source of truth. It scores fixed categories (each normalized 0–10) from explicit file and rule checks, and the same commit always yields the same score:
- Tool Coverage
- Context Efficiency
- Quality Gates
- Memory Persistence
- Eval Coverage
- Security Guardrails
- Cost Efficiency
Scoped audits include only the categories that apply (
applicable_categories). Report therubric_versionthe script prints; do not add dimensions or points. -
Return:
overall_scoreout ofmax_score, as reported- category scores and concrete findings
- failed checks with exact file paths from
checks[] - the top three actions from
top_actions[] - suggested everything-claude-code skills that address the failing categories
With
--format json, return the script JSON unchanged and nothing else. With text, summarize failing checks and top actions.
Example result
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.
- 14d ago Changed · -1 lines · +32 tokens per session 24981103bf19
- 1mo ago First seen · 76 lines · 15 tokens per session scan A 74c0d55a4300
ccc-harness-audit is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 778 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to harness-audit, differing in 93 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.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.