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 rules/wojisama/skill-based-architecture/frontendgit clone --depth 1 https://github.com/WoJiSama/skill-based-architectureWhat 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 | $0.00005 | $0.00197 |
| Opus 5 | $0.00003 | $0.00098 |
| Sonnet 5 | $0.00001 | $0.00039 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
frontend 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 3d 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.
What it actually says
Frontend Rules
- Use
summarizeCartfor cart display data; do not duplicate subtotal math in UI components. - Keep raw cent values available for calculations and analytics.
- Format display values only with
formatMoney. - Show subtotal and total together when a discount is active.
Add UI Component Flow
- Confirm the component needs cart data.
- Use
summarizeCartfor derived values. - Keep component state in raw cents, not formatted strings.
- Test a discounted and non-discounted cart.
Pitfalls
- If a component stores
"$12.99"in state, later discount math has to parse a display string and can drift. - Cursor-only frontend rules drift from
AGENTS.mdandCLAUDE.md; this should becomeskills/demo-shop/rules/frontend-rules.md.
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.
- 3d ago First seen · 27 lines · 5 tokens per session scan A b73387283beb
frontend is a cursor rule published in the GitHub repository WoJiSama/skill-based-architecture (547 stars, last pushed 19d ago), licensed MIT. It adds 5 tokens to every session and 197 once invoked, about $0.0000 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 2026-08-30.
Other cursor rules, from other repositories
frontend-theme-guidelines
Cursor rule "frontend-theme-guidelines" from KroMiose/nekro-agent, covering 前端主题系统开发指南, 主题系统架构, 核心文件结构, 基本原则 and 主题使用指南.
frontend-css
Cursor rule "frontend-css" from tomasz-tomczyk/crit, covering css rules, responsive & touch and selectors.
she-love-me
End-to-end WeChat or QQ relationship analysis workflow.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
global
Cursor rule "global" from KroMiose/nekro-agent, covering 项目背景（简要）, 开发规范, 文档, 开发指南 and 功能/页面开发完整流程.
use-bun-instead-of-node-vite-npm-pnpm
../../CLAUDE.md.