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 instructions/justjavac/glitch-token/agents-mdgit clone --depth 1 https://github.com/justjavac/glitch-tokenWrote 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/justjavac/glitch-token/agents-md)<a href="https://agentmods.dev/instructions/justjavac/glitch-token/agents-md"><img src="https://agentmods.dev/badge/instructions/justjavac/glitch-token/agents-md.svg" alt="Measured on agentmods" 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 | $0.00903 | $0.00903 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
glitch-token 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is NOT the Next.js you know
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ (resolved from this file's directory; in monorepos the next package may not be visible from the repo root) before writing any code. Heed deprecation notices.
This block is written and re-added by next dev — verify at node_modules/next/dist/server/lib/generate-agent-files.js. Removing it from a diff only re-creates the uncommitted change; committing it with your work keeps the tree clean.
开发者文档
技术栈
- Next.js
16.3.0-preview.6（App Router，全静态 SSG）+ React 19 + TypeScript - Tailwind CSS v4 + shadcn/ui（@base-ui/react 变体）
- 暗色/明亮双主题（next-themes，默认跟随系统）；中英双语（
/zh、/en，src/proxy.ts按 Accept-Language 重定向） - 数据：
src/data/（内置静态数据，无后端）
命令
# 本机通过 corepack 使用 pnpm（如 pnpm 不在 PATH，可用 corepack pnpm 代替）
corepack pnpm install
corepack pnpm dev # 开发
corepack pnpm build # 构建（全部页面静态预渲染，含数据校验）
corepack pnpm start # 生产模式
corepack pnpm lint # ESLint
站点 URL
生产构建必须设置 SITE_URL（用于 canonical/hreflang/sitemap/OG 的绝对 URL）。正式域名为 https://glitch-token.jjc.fun，已在 Vercel 项目环境变量中配置；本地生产构建用：
SITE_URL=https://glitch-token.jjc.fun corepack pnpm build
开发环境未设置时使用 http://localhost:3000；生产环境缺失或格式无效会直接终止构建，避免搜索引擎收录 localhost URL。
结构
src/app/[lang]/— 双语路由（首页目录 +tokens/[id]详情页 +models/[id]聚合页，全部 SSG）src/app/tokens.json/、src/app/llms.txt/、src/app/llms-full.txt/— 面向程序/LLM 的静态输出src/app/sitemap.ts、src/app/robots.ts、src/app/icon.svg、public/og.png— SEO 与站点图标/分享图src/proxy.ts— Next 16 的 proxy（原 middleware）：语言协商与重定向src/data/—types.ts/models.ts/tokens.ts/taxonomy.ts/validate.ts数据层src/i18n/— UI 文案字典（zh/en）src/components/— 目录筛选（catalog-filters.tsx，Select）、token 卡片、主题/语言切换、GitHub 链接、复制按钮等
数据约定
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.
- 4d ago First seen · 58 lines · 903 tokens per session scan A 33249d6ca063
glitch-token AGENTS.md is an instructions file published in the GitHub repository justjavac/glitch-token (11 stars, last pushed 1mo ago), licensed MIT. It adds 903 tokens to every session, about $0.0045 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 instructions, from other repositories
einbiogpt copilot-instructions.md
Instructions for ehsanghaffar/einbiogpt, covering biogpt copilot instructions, project architecture, rate limiting & error handling, key patterns & conventions and environment variables.
einbiogpt AGENTS.md
Instructions for ehsanghaffar/einbiogpt, covering agents.md - coding guidelines for ai agents, project overview, build/development commands, development server and production build.
LightRAG AGENTS.md
AGENTS.md instructions for HKUDS/LightRAG, covering repository guidelines, project overview, project structure, module layout (lightrag/) and core architecture.
agentscope copilot-instructions.md
Copilot instructions for agentscope-ai/agentscope, covering agentscope code review guide, 1. code quality, 2. [must] code security, 3. [must] testing & dependencies and 4. code standards.
CopilotKit AGENTS.md
AGENTS.md instructions for CopilotKit/CopilotKit, covering general guidelines for working with nx, copilotkit, essentials, private agent instructions and internal skills.
CopilotKit CLAUDE.md
Claude Code instructions for CopilotKit/CopilotKit, covering general guidelines for working with nx, copilotkit, essentials and reference (read when relevant to your task).