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/ndisisnd/cook/cssnpx skills add ndisisnd/cook --skill cssgit clone --depth 1 https://github.com/ndisisnd/cookWhat 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 | $0.00080 | $0.01892 |
| Opus 5 | $0.00040 | $0.00946 |
| Sonnet 5 | $0.00016 | $0.00378 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
css 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSS
CSS is forgiving and subjective — there is rarely one "correct" stylesheet. Optimise for consistency, low specificity, and not breaking the user, not for rule-compliance. This file is the whole standard for most styling work; pull a ref only when you need depth.
The single biggest lever is matching what the codebase already does. A convention you'd not have picked, applied consistently, beats a "better" one applied unevenly. Propose a methodology or tooling migration (BEM ↔ utilities, adding Tailwind, swapping Sass) as its own explicit task — never as a drive-by inside a feature change.
Principles (battle-tested)
- Keep specificity low and flat. Style with a single class, keep selectors shallow, and avoid IDs and
!important. Low, even specificity is what keeps styles overridable — most CSS pain is a specificity war that someone started and everyone else inherited. When cascade order genuinely matters, control it with@layer, not by piling on selectors. →refs/architecture.md - Scope by default. Leaking styles is the root cause of most "why did that change?" bugs. Reach for CSS Modules, a naming convention (BEM/utilities), or
@scope; keep bare element selectors to resets and base. →refs/architecture.md - Tokenize; don't hardcode. Keep one source of truth for colour, spacing, and type. Use custom properties for anything themeable, and derive values from a scale instead of scattering magic numbers. →
refs/theming.md - Lay out with Flexbox and Grid. They solve cleanly what floats, absolute positioning, and fixed heights only ever hacked around. Reach for
gap, intrinsic sizing, and container queries before adding media queries. →refs/layout.md - Use the platform; don't over-tool. Modern CSS (nesting, custom properties,
clamp(),color-mix()) covers most of what preprocessors were for. Add Sass/PostCSS/Tailwind because the team gets real leverage from it, not by reflex — and don't ship a shiny new feature to production without checking your browser support. →refs/tooling.md,refs/tailwind.md - Prefer deleting and composing over overriding. CSS only ever grows, and every override is future debt. If you're writing a rule to defeat another rule, fix the first one instead.
What ships with it
9 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.
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 · 96 lines · 80 tokens per session scan A c1bc850c53fd
css is a skill published in the GitHub repository ndisisnd/cook (2 stars, last pushed 21d ago), licensed MIT. It adds 80 tokens to every session and 1,892 once invoked, about $0.0004 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
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
wechat-article-writer
公众号/自媒体全流程。根据用户表述自动匹配:撰写文章、封面图、正文插图、风格提取。支持多种写作风格。当用户提到写公众号、技术博客、公众号封面、正文插图、步骤图、演示图、流程示意、分析写作风格、克隆文风、模仿爆款、提取风格时使用。详见 reference 目录。.
miniapp-dev
Develops, maintains, and generates BitFun MiniApps (Zero-Dialect Runtime). Use when (1) working on miniapp framework code under src/crates/assembly/core/src/miniapp/ or src/web-ui/src/app/scenes/miniapps/; or (2) generating / creating / designing a NEW MiniApp for the user — including any request like "做一个小应用 / 生成…
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…