Borrowing it
Nothing to install: this file belongs to n9e/fe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/n9e/fe/main/AGENTS.mdgit clone --depth 1 https://github.com/n9e/feWrote 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/instructions/n9e/fe/agents-md)<a href="https://agentmods.dev/instructions/n9e/fe/agents-md"><img src="https://agentmods.dev/badge/instructions/n9e/fe/agents-md/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/instructions/n9e/fe/agents-md"><img src="https://agentmods.dev/badge/instructions/n9e/fe/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01878 | $0.01878 |
| Opus 5.5 | $0.00751 | $0.00751 |
| Sonnet 5.5 | $0.00376 | $0.00376 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
fe AGENTS.md 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 6d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Instructions
- After making code changes, do not run
npm run buildornpx tscunless the user explicitly asks for it. - If verification is useful, prefer lighter checks that are relevant to the changed files, or ask before running expensive project-wide commands.
- After modifying source files, run
./node_modules/.bin/prettier --writeon the changed files and verify them with./node_modules/.bin/prettier --checkbefore delivery. Follow.prettierrc.json; do not leave formatting-only violations in changed files. - Prefer native type-checking APIs over lodash for type narrowing: use
Array.isArrayinstead of_.isArray,typeof x === 'number'instead of_.isNumber,x == nullinstead of_.isNil, etc. Lodash type guard functions are not recognized by TypeScript when@types/lodashis unavailable, leavingunknowntypes un-narrowed.
页面修改原则
- 所有页面修改都要检查视觉美观与周边协调,包括按钮间距、水平/垂直对齐、颜色、图标与文字的实际可见间距;不能只检查控件外框或功能是否可用。
- 提示浮窗按内容调整宽度:不超过 20 个字的短句尽量保持一行,避免过窄造成无意义换行;长文案与窄视口仍须合理换行,不能溢出屏幕。背景与箭头使用系统 Tooltip 的主题、颜色及透明度,与“筛选”旁的提示一致,不单独硬编码不透明背景。
- 所有修改都要控制影响范围,优先采用页面或组件局部作用域;检查相关状态、共用组件调用方与集成入口,避免修复一处却让其他位置回归,并完成与改动相关的验证。
React Router Routes and Deployment Prefixes
- This project uses React Router's
basenamefor subpath deployments. Use Router-provided paths for in-app routes. For example, with a/flashcatbasename,useLocation().pathnameand React Router'shistory.location.pathnameare/dial-analysis, whilewindow.location.pathnameor globallocation.pathnameis the full browser path/flashcat/dial-analysis. - When building in-app navigation, calling React Router's
history.pushorhistory.replace, or preserving the current route, use Router-relative paths such asuseLocation()orhistory.location. Do not use globallocation.pathnameas a Router path or prependbasenameto a Router path; either can duplicate the prefix and produce a URL such as/flashcat/flashcat/polaris. useLocation()is a snapshot for the current render. If an asynchronous callback needs the latest path or query string when it runs, readhistory.locationfrom the corresponding Router history instead of relying on a stale value captured by a closure.- Use
window.locationor globallocationonly when browser-level URL semantics are needed, such as a full-page navigation, reload, or generating a browser URL that includes the deployment prefix. Their paths have different semantics from Router paths. The native History API onwindow.historyis also different from React Router'shistory. - For copied, shared, saved, or custom-generated URLs, first distinguish a Router path, an app-relative URL, and a fully qualified URL. Use the existing URL helpers (
getAppBaseUrlandaddAppBasePrefixinsrc/utils/appUrl.ts) instead of concatenatingbasePrefixad hoc. The helper leaves absolute URLs untouched and avoids duplicating an existing prefix. $local_urlis a fully qualified app base URL, including origin and deployment prefix. After expanding it, do not prependbasePrefixagain. Likewise,window.location.pathnamealready includes the browser prefix, whileuseLocation().pathnamedoes not.- The Vite prefix plugin rewrites recognized URL sinks such as direct
window.opencalls; it does not rewrite URLs copied to the clipboard, displayed in inputs, stored in config/data objects, or passed through custom components. Handle those values explicitly with the URL helpers.
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.
- 6d ago Changed · +17 lines · +793 tokens per session c60929805d1a
- 9d ago Changed · +10 lines · +482 tokens per session 325f1121f52e
- 14d ago Changed · +7 lines · +244 tokens per session 79d02a3ed22e
- 1mo ago Changed · +1 lines · +60 tokens per session 2767e40dc5f1
- 1mo ago First seen · 12 lines · 299 tokens per session scan A 50cf08635a34
fe AGENTS.md is an instructions file published in the GitHub repository n9e/fe (308 stars, last pushed today), licensed Apache-2.0. It adds 1,878 tokens to every session, about $0.0075 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 2026-09-01.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.