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-theme)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-theme"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-theme/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-theme"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-theme.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 | $0.01268 |
| Opus 5.5 | $0.00019 | $0.00507 |
| Sonnet 5.5 | $0.00009 | $0.00254 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
ccc-theme scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-theme — switch the terminal skin
CC Commander · /ccc-theme · reads the theme definitions from lib/themes.js and writes the chosen theme to the Commander config.
Themes
| Skin | ID | Look |
|---|---|---|
| Claude Anthropic | claude |
Warm amber #D97706 on deep navy #0F0F1A (default) |
| OLED Black | oled |
White #FFFFFF on pure black #000000 |
| Matrix | matrix |
Green #00FF41 on black #0A0A0A |
| Surprise Me | random |
One curated palette per session: cyberpunk, sunset, arctic, coral, neon |
The definitions live in lib/themes.js (THEMES, RANDOM_PALETTES) and lib/themes.sh. The installed copy is under ~/.claude/lib/; in a repo checkout use lib/. Below, THEMES_JS means whichever of those exists:
THEMES_JS="$HOME/.claude/lib/themes.js"; [ -f "$THEMES_JS" ] || THEMES_JS="$PWD/lib/themes.js"
Arguments
$ARGUMENTS is one of list, set <name>, preview <name>, random. Empty means list followed by the picker in step 2 of set.
What happens
list
Print every theme with its colors and mark the active one:
node -e 'const t=require(process.argv[1]); const a=t.getTheme().name; for (const [id,v] of Object.entries(t.THEMES)) console.log((v.name===a?"● ":" ")+id.padEnd(8)+v.name+" bg "+v.css.bg+" primary "+v.css.primary+" accent "+v.css.accent); console.log(" random palettes: "+t.RANDOM_PALETTES.map(p=>p.name).join(", "))' "$THEMES_JS"
preview <name>
Show the theme without switching: print THEMES[<name>].css (bg, primary, accent, emerald) and a sample line in its ANSI colors:
node -e 'const t=require(process.argv[1]).THEMES[process.argv[2]]; if(!t){console.error("unknown theme");process.exit(1)} console.log(t.name, t.css); console.log(t.primary+"primary "+t.accent+"accent "+t.success+"success "+t.warn+"warn "+t.error+"error"+t.reset)' "$THEMES_JS" <name>
set <name>
- Validate
<name>againstclaude,oled,matrix,random. If it is missing or unknown, ask with AskUserQuestion (plain-text question where it is unavailable): 🟢 claude (default, amber on navy) · oled (white on black, for OLED screens) · matrix (green on black) · random (new palette each session). - Write the choice to
~/.claude/bible-config.json, preserving every other key:
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 · +4 lines · +28 tokens per session 453cb7ee6f65
- 1mo ago First seen · 81 lines · 19 tokens per session scan A b83e194372c8
ccc-theme is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,268 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 2026-09-04.
Other commands, from other repositories
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
steve-skills
Invoke Steve Jobs — Design & Simplicity. Use for product vision sharpening, radical simplicity, UX design, storytelling, and presentation preparation.
justone
Start a Just One Prompt Challenge — ship a runnable project from a single prompt.
design-review
Run the 7-phase design review (WCAG AA, responsive, interaction) on a page or URL.
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.