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 skills/livlign/ccthemes/theme-customnpx skills add livlign/ccthemes --skill theme-customgit clone --depth 1 https://github.com/livlign/ccthemesWrote 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/skills/livlign/ccthemes/theme-custom)<a href="https://agentmods.dev/skills/livlign/ccthemes/theme-custom"><img src="https://agentmods.dev/badge/skills/livlign/ccthemes/theme-custom.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 | $0.00056 | $0.00876 |
| Opus 5 | $0.00028 | $0.00438 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade B, and why
theme-custom scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` (create `{}` if absent), set `"theme": "custom:<slug>"`, How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a custom Claude Code theme
Guide the user to a finished, activated custom theme. A theme is a JSON file at
~/.claude/themes/<slug>.json with three fields: name, base, and overrides.
Claude Code hot-reloads the folder, so a written file applies without restart
(if ~/.claude/themes/ did not exist before this session, the user restarts once).
Steps
-
Establish the direction. Ask two quick questions if the user hasn't already said:
- Light or dark? → sets
base(darkis the default;light,dark-daltonized,light-daltonized,dark-ansi,light-ansiare the other options). - A hero/accent color or a vibe (e.g. "warm terracotta", "cool neon", "muted forest").
Offer to start from an existing shipped theme as a base to tweak — read one from the
plugin's
themes/directory and adjust it.
- Light or dark? → sets
-
Generate the overrides. Only set tokens you have a deliberate reason to change; everything else inherits from
base. Colors accept#rrggbb,#rgb,rgb(r,g,b),ansi256(n), oransi:<name>. The tokens that matter most, in priority order:Token Controls claudePrimary accent — spinner, assistant label. Set claudeShimmerto a lighter tint of it.textDefault foreground text inactive/subtleHints, timestamps; faint borders success/error/warningPass / fail / caution diffAdded/diffRemovedBackgrounds of added/removed lines — use dark, desaturated tints on dark bases and pale tints on light bases, NOT vivid foreground green/red diffAddedWord/diffRemovedWordWord-level highlight, a shade stronger than the line diffAddedDimmed/diffRemovedDimmedFaint context tint near a change planMode/autoAccept/bashBorder/promptBorderMode accents and input borders Rule of thumb for diff backgrounds: composite the theme's green/red over its background at low alpha (~18–22% on dark, ~16% on light). Never reuse a vivid terminal foreground green as a background — it destroys the text contrast.
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 First seen · 57 lines · 56 tokens per session scan B a0c8c1f663bf
theme-custom is a skill published in the GitHub repository livlign/ccthemes (2 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 876 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
ops-pocket
OPS on-demand: This skill should be used when the user asks to "pocket memos", "voice memo pipeline"…
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.