ccc-usage SKILL.md skillA

ccc-usage from kevinzai/commander is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add kevinzai/commander/ccc-usage@git:20261013.fbe187d

Pins git:20261013.fbe187d in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: kevinzai/commander
Path: commander/cowork-plugin-codex/skills/ccc-usage/SKILL.md
Versions recorded: 4
Latest version: git:20261013.fbe187d, committed Oct 13, 2026
First version recorded: Jul 20, 2026
Size: 4,829 bytes
Repository stars: 6
License: MIT

Usage and cost deck: estimated savings from routing to cheaper models, cost per day and cost by app, narrated here or published as a private snapshot page after consent. Use when the user asks what agent work costs, how much was saved, or types $ccc-usage.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# $ccc-usage — what the work cost

**CC Commander** · $ccc-usage · estimated savings, spend per day and spend per app from local logs.

Sources: `~/.claude/commander/savings.json` (estimated savings versus an all-Opus baseline) and `~/.claude/commander/mission-control/metrics.jsonl` (cost per app per day). These are estimates from per-model rates, not a bill; say so whenever you quote a number.

## When to use / when not to

- Use for "what did this cost?", "how much did delegation save?", or a shareable cost page.
- Use `$ccc-console usage` for the same tab inline beside the other tabs. For an actual bill, use the provider's billing page; this deck only estimates.

## What happens

### 1. Pick the output

With no argument, ask with AskUserQuestion (Codex: a plain-text question):

- 🟢 Plain-English status — the headline numbers here, nothing leaves the machine
- Publish the deck — a private claude.ai page; asks before uploading
- Show it inline — runs `$ccc-console usage`

`status` goes to step 2. `open` or `snapshot` goes to step 3.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add kevinzai/commander/ccc-usage@sha256:111d23762abcce75

The line at the top of this page pins the label git:20261013.fbe187d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_tyhbl45q5l6ydbmy.svg)](https://markdownregistry.com/a/art_tyhbl45q5l6ydbmy)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 20, 2026 and Oct 13, 2026, about one every 28 days.

version	committed	commit	size	audit
git:20261013.fbe187d latest	2026-10-13	fbe187d	4,829 B	A	view · diff
git:20260728.38c269b	2026-07-28	38c269b	4,532 B	A	view · diff
git:20260722.9d3ab82	2026-07-22	9d3ab82	4,104 B	A	view · diff
git:20260720.7ee5b5c	2026-07-20	7ee5b5c	3,492 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (4829 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

kevinzai/commander · 6 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tyhbl45q5l6ydbmy
GET https://markdownregistry.com/api/v1/resolve?ref=kevinzai/commander/ccc-usage
GET https://markdownregistry.com/api/v1/blob/111d23762abcce758f36a5e8bdfb12fd34016cf6846c9c547ac28d977acc28d6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from kevinzai/commander

mintlify SKILL.md skill

kevinzai/commander · .agents/skills/mintlify/SKILL.md · Build and maintain documentation sites with Mintlify. Use when

v1.0 · audit A · 6 stars

.cursorrules Cursor rule

kevinzai/commander · .cursorrules

git:20260327.b10b207 · audit A · 6 stars

AGENTS.md AGENTS.md file

kevinzai/commander · AGENTS.md