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/quantumentangled-dev/ai-docs-plugin/themenpx skills add quantumentangled-dev/ai-docs-plugin --skill themegit clone --depth 1 https://github.com/quantumentangled-dev/ai-docs-pluginWhat 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 | $0.00155 | $0.01354 |
| Opus 5 | $0.00077 | $0.00677 |
| Sonnet 5 | $0.00031 | $0.00271 |
| Haiku 4.5 | $0.00015 | $0.00135 |
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 yesterday.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
theme
Apply, change, or remove a visual theme on a built ai-docs .html. Theme is a post-build CSS injection — the .md source stays untouched.
How themes are stored
Each theme is two files under ${CLAUDE_PLUGIN_ROOT}/skills/theme/themes/<slug>.{md,css}:
.md— palette, typography, "best for" guidance (human + LLM reading).css— slide chrome + CSS custom-property declarations consumed by the sharedtemplates/mermaid-overrides.css.tpl
The .css + the shared mermaid override template are concatenated into a single <style data-ai-docs-theme="<slug>">…</style> block injected immediately before </head>, preceded by a <!-- ai-docs-theme: <slug> --> marker line. The marker is the source-of-truth for "what theme is on this doc"; the builder reads it on rebuild so theme persists across edits.
Available themes
10 themes ship with the plugin. To see them all with palette swatches, run list mode (below).
| Slug | Vibe |
|---|---|
arctic-frost |
cool / crystalline |
botanical-garden |
verdant / lush |
desert-rose |
warm / earthy |
forest-canopy |
organic / grounded |
golden-hour |
warm / optimistic |
midnight-galaxy |
dark / cosmic |
modern-minimalist |
clean / neutral |
ocean-depths |
deep / oceanic |
sunset-boulevard |
vibrant / cinematic |
tech-innovation |
sharp / technical |
When to fire
Should trigger — apply:
- "apply forest-canopy to login-deck"
- "theme the q2 report with midnight-galaxy"
- "use the desert-rose look on my deck"
- "switch the theme to modern-minimalist"
- "/ai-docs:theme tech-innovation"
Should trigger — list:
- "what themes are available?"
- "show me the themes"
- "/ai-docs:theme list"
Should trigger — remove:
- "remove the theme from login-deck"
- "unstyle my deck"
- "/ai-docs:theme none login-deck"
Should NOT trigger:
- "create a forest-canopy deck about X" →
createskill (theme is picked at creation time) - "publish the themed deck" →
publishskill - "what does my deck look like?" → not a theme operation; offer to open
.html
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/apply-theme.sh 5.6 KB runs code
- scripts/get-theme.sh 839 B runs code
- scripts/list-themes.sh 1.1 KB runs code
- templates/mermaid-overrides.css.tpl 13 KB
- themes/arctic-frost.css 2.1 KB
- themes/arctic-frost.md 697 B
- themes/botanical-garden.css 2.0 KB
- themes/botanical-garden.md 728 B
- themes/desert-rose.css 2.0 KB
- themes/desert-rose.md 722 B
- themes/forest-canopy.css 2.1 KB
- themes/forest-canopy.md 837 B
- themes/golden-hour.css 2.0 KB
- themes/golden-hour.md 731 B
- themes/midnight-galaxy.css 2.1 KB
- themes/midnight-galaxy.md 855 B
- themes/modern-minimalist.css 2.0 KB
- themes/modern-minimalist.md 745 B
- themes/ocean-depths.css 2.0 KB
- themes/ocean-depths.md 725 B
- themes/sunset-boulevard.css 2.1 KB
- themes/sunset-boulevard.md 726 B
- themes/tech-innovation.css 2.1 KB
- themes/tech-innovation.md 829 B
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.
- yesterday First seen · 123 lines · 0 tokens per session scan A 46ec4ea265f1
theme is a skill published in the GitHub repository quantumentangled-dev/ai-docs-plugin (6 stars, last pushed 3mo ago), licensed MIT. It adds 155 tokens to every session and 1,354 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…