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.
npx agentmods add commands/kevinzai/commander/ccc-themegit 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.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00665 |
| Opus 5 | $0.00010 | $0.00332 |
| Sonnet 5 | $0.00004 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
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 today.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Theme — Visual Skin Switcher
Available Themes
| Skin | ID | Description |
|---|---|---|
| Claude Anthropic | claude |
Professional warm amber on deep navy (DEFAULT) |
| OLED Black | oled |
Pure black background for OLED displays |
| Matrix | matrix |
Classic green-on-black with CRT scanline effect |
| Surprise Me | random |
Random curated palette each session |
Subcommands
/theme list
Display all available themes with color swatches:
THEMES:
● claude — Warm amber (#D97706) on deep navy (#0F0F1A) [DEFAULT]
● oled — White (#FFFFFF) on pure black (#000000)
● matrix — Matrix green (#00FF41) on black (#0A0A0A)
● random — Surprise palette (cyberpunk / sunset / arctic / coral / neon)
/theme set [name]
Switch to a theme. Sets CC_THEME in bible-config.json and updates the dashboard.
- Validate theme name against available options
- Update
~/.claude/bible-config.json→"theme": "[name]" - If dashboard is running, it picks up the change via localStorage
- Confirm:
Theme set to [name]. Terminal colors will apply on next session.
/theme preview [name]
Show a color swatch preview without switching:
THEME PREVIEW: Matrix
Background: ██ #0A0A0A
Primary: ██ #00FF41
Secondary: ██ #00CC33
Accent: ██ #00FFFF
Success: ██ #00FF00
Warning: ██ #FFAA00
Error: ██ #FF0000
/theme random
Apply a random palette from the curated pool:
- Cyberpunk (Pink + Electric Blue)
- Sunset (Orange + Purple)
- Arctic (Ice Blue + Frost — Nord-inspired)
- Coral Reef (Coral + Teal)
- Neon (Lime + Hot Pink)
Shows which palette was selected.
Configuration
- Config file:
~/.claude/bible-config.json→"theme": "claude" - Env override:
CC_THEME=matrix(takes precedence over config) - Dashboard: Reads from localStorage
cc-dashboard-theme - Terminal hooks: Read from config via
lib/themes.js→getTheme()
Integration
- Terminal art (
lib/terminal-art.sh) sourceslib/themes.shfor color vars - Node hooks (
hooks/*.js) importlib/themes.jsfor ANSI codes - Dashboard CSS loads
themes/*.cssbased ondata-themeattribute - iTerm2 profiles available in
compatibility/for each theme
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.
- today First seen · 81 lines · 19 tokens per session scan A b83e194372c8
theme is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 665 once invoked, about $0.0001 per session on Opus 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
specmanager-design
Design the actual screens for a SpecManager feature as stacked high-fi HTML mockups via the designer subagent. Optional — Plan can run without one, but if a draft exists, Plan refuses to open until it's approved.
my_brand
Interactive brand identity creation with archetypes, colors, typography, and voice guidelines. Use when user mentions "brand", "colors", "typography", "brand.md", "design system", or "visual identity".
ux-spec
Six-layer spec.md via the S0-S6 shaping session (question/assumption/confirmation batches + session artifacts); stop before UI shell/code.
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
figma
Convert a Figma design to production code. Provide a Figma URL or select a node in Figma desktop.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.