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 skills add bovinphang/frontend-craft --skill fec-data-fetchinggit clone --depth 1 https://github.com/bovinphang/frontend-craftWrote 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/bovinphang/frontend-craft/fec-data-fetching)<a href="https://agentmods.dev/skills/bovinphang/frontend-craft/fec-data-fetching"><img src="https://agentmods.dev/badge/skills/bovinphang/frontend-craft/fec-data-fetching/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bovinphang/frontend-craft/fec-data-fetching"><img src="https://agentmods.dev/badge/skills/bovinphang/frontend-craft/fec-data-fetching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00076 | $0.00778 |
| Opus 5.5 | $0.00030 | $0.00311 |
| Sonnet 5.5 | $0.00015 | $0.00156 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
fec-data-fetching 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 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.
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
Server State 数据获取
用途
为前端 server state 建立清晰的数据获取、缓存、失效和提交边界,避免请求状态散落在页面组件中。
流程
- 判断状态来源:来自服务端且需要缓存、去重、刷新、分页或 mutation 时使用请求缓存方案;纯本地 UI 状态用组件 state 或 store。
- 先沿用项目已有数据获取库;新增依赖时 React/Vue/Solid/Svelte 可考虑 TanStack Query,也可沿用 SWR、Nuxt/Nitro 数据获取或项目封装。
- 设计稳定 cache key/query key:结构包含实体、动作和所有影响结果的参数。
- API 函数保持纯请求函数,数据 hook/composable 负责缓存、select、loading/error/empty 状态。
- mutation 成功后 invalidation;需要即时反馈时使用 optimistic update 并在失败时回滚。
React 快速开始
import { useMutation, useQuery, useQueryClient } from "@tanstack/react-query";
export function UserList({ keyword }: { keyword: string }) {
const query = useQuery({
queryKey: ["users", "list", { keyword }],
queryFn: () => getUserList({ keyword, page: 1, pageSize: 20 }),
select: (response) => response.list,
});
if (query.isLoading) return <Skeleton />;
if (query.isError) return <ErrorFallback onRetry={() => query.refetch()} />;
if (!query.data?.length) return <EmptyState />;
return query.data.map((user) => <UserRow key={user.id} user={user} />);
}
export function useCreateUser() {
const queryClient = useQueryClient();
return useMutation({
mutationFn: createUser,
onSuccess: () => queryClient.invalidateQueries({ queryKey: ["users"] }),
});
}
详细参考
涉及是否需要查询库、QueryClient 默认配置、Vue adapter、乐观更新、无限滚动查询、预取、SSR 水合和 API 层整合时,加载 references/query-patterns.md。
约束
- 相同数据必须复用相同 cache key/query key;参数缺失会造成缓存串读。
staleTime过长会显示旧数据,过短会造成频繁请求。- 请求缓存库不管理本地 UI 状态;不要把 modal、输入框值放进 query cache。
- 乐观更新必须保存快照并在失败时回滚。
- SSR/SSG 场景必须使用框架支持的预取、水合或服务端数据边界。
预期输出
数据获取层具备 loading/error/empty/data 状态,重复请求自动去重,mutation 后缓存正确失效或回滚,API 层与 UI 层边界清晰。
工程实践
按当前任务读取本入口工程细则,再按链接选择公共原则。规则级别与例外以实际项目契约为准;不因产品前后端标签限制语言或职责。
What ships with it
2 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.
- 5d ago Changed · +4 lines 597b728cf896
- 2mo ago First seen · 63 lines · 76 tokens per session scan A 3c1832fa8133
fec-data-fetching is a skill published in the GitHub repository bovinphang/frontend-craft (24 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 778 once invoked, about $0.0003 per session on Opus 5.5. 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.
fec-data-fetching compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fec-data-fetchingbovinphang/frontend-craft | Skill | 24 | yesterday | MIT | A | 76 | Claude Code |
| adhdszarkans/multi | Skill | 24 | 11d ago | MIT | A | 124 | Claude Code |
| validate-apijohnkozaris/jko-claude-plugins | Skill | 11 | 9d ago | MIT | A | 20 | Claude Code |
| backend-architecturejohnkozaris/jko-claude-plugins | Skill | 11 | 9d ago | MIT | A | 119 | Claude Code |
| validate-wsjohnkozaris/jko-claude-plugins | Skill | 11 | 9d ago | MIT | A | 19 | Claude Code |
| brand-designrfxlamia/pocketto | Skill | 6 | 14d ago | MIT | B | 146 | Claude Code |
| dotnet-backend-expertmathisk2095/jko-claude-plugins | Skill | 3 | 1mo ago | MIT | A | 181 | Claude Code |