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/anoopsg/agent_rules/extend-themenpx skills add anoopsg/agent_rules --skill extend-themegit clone --depth 1 https://github.com/anoopsg/agent_rulesWhat 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 | $0.00046 | $0.01071 |
| Opus 5 | $0.00023 | $0.00535 |
| Sonnet 5 | $0.00009 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
extend-theme scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Theme Extension Skill
This skill defines the process for adding or modifying a design token in
packages/app_ui's theme system, which is built on two
ThemeExtensions — AppColors and AppTextTheme — each implemented in
four variants.
1. Structure
packages/app_ui/lib/src/
├── colors/
│ ├── app_colors.dart # Base ThemeExtension: fields, copyWith, lerp
│ ├── app_colors_light.dart
│ ├── app_colors_dark.dart
│ ├── app_colors_high_contrast_light.dart
│ └── app_colors_high_contrast_dark.dart
├── typography/
│ ├── app_text_theme.dart # Base ThemeExtension: fixed M3 type scale
│ └── text_theme_native.dart
└── themes/
├── app_theme.dart # Composes colors + textTheme into ThemeData
├── app_theme_light.dart
├── app_theme_dark.dart
├── app_theme_high_contrast_light.dart
└── app_theme_high_contrast_dark.dart
Access at the call site is always through the context.$ shorthand
(packages/app_ui/lib/src/tokens/app_tokens.dart), never
Theme.of(context).extension<...>() directly:
context.$.colors.primary
context.$.style.bodyLarge
2. Adding a New Color Token
There is no per-variant token map — AppColors is a fixed
constructor with one field per token, so a new token must be added to
every layer:
app_colors.dart(base class): add the field, the constructor parameter, thecopyWithparameter + fallback, and thelerpentry (Color.lerp(fieldName, other.fieldName, t)!). Every list must be updated together or the extension breaks.- Each of the 4 variant files (
app_colors_light.dart,app_colors_dark.dart,app_colors_high_contrast_light.dart,app_colors_high_contrast_dark.dart): supply a concreteColorvalue for the new field in thesuper(...)call. - Pick values by role, not by copying an existing color — check
whether an existing token already fits before adding a new one (a new
token is for a genuinely new semantic role, e.g.
warning/onWarning, not a one-off shade).
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.
- 2d ago First seen · 107 lines · 46 tokens per session scan A 6e6980315d2f
extend-theme is a skill published in the GitHub repository anoopsg/agent_rules (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,071 once invoked, about $0.0002 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
web-design-guidelines
UI/UX best practices and accessibility audit. Use when reviewing UI code, checking accessibility, running accessibility audits, auditing forms, or ensuring web interface best practices. Triggers on "audit accessibility", "check WCAG", "review UI", "check accessibility", "audit design", "review UX", or "check best…
marketing-psychology
Apply psychological principles and behavioral design to product copy, onboarding flows, landing pages, feature descriptions, CTAs, and pricing tiers. Covers cognitive biases (loss aversion, social proof, anchoring, paradox of choice, Zeigarnik effect, IKEA effect, reciprocity, commitment & consistency) and the Fogg…
design-guide
Paperclip UI design system guide for building consistent, reusable frontend components. Use when creating new UI components, modifying existing ones, adding pages or features to the frontend, styling UI elements, or when you need to understand the design language and conventions. Covers: component creation, design…
gstack-openclaw-office-hours
Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.