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/sabertaz/blog/agents-mdgit clone --depth 1 https://github.com/sabertaz/blogWrote 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/sabertaz/blog/agents-md)<a href="https://agentmods.dev/instructions/sabertaz/blog/agents-md"><img src="https://agentmods.dev/badge/instructions/sabertaz/blog/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 | $0.01670 | $0.01670 |
| Opus 5 | $0.00835 | $0.00835 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
blog 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
Quick Start
# First time setup
pnpm install # ~15-20s
pnpm playwright install --with-deps # E2E browsers (first time only)
# Development
pnpm dev # Start dev server at localhost:3000 (~1s)
# Common Tasks
pnpm lint # Run all linters (~5-10s)
pnpm lint:fix # Auto-fix linting issues
pnpm test # Unit tests (watch mode)
pnpm test:all # Unit tests with coverage (~35-40s)
pnpm e2e # E2E tests (~5-10min, includes build)
pnpm build # Production build (~30-40s)
# Important: Always use pnpm (never npm/yarn)
Architecture Overview
Modern bilingual blog built with Next.js App Router, featuring i18n, MDX content, animations, and comprehensive testing.
Core Stack
- Next.js with App Router and Turbopack
- React with React Compiler enabled (automatic optimizations)
- TypeScript in strict mode
- Tailwind CSS (no config file, uses PostCSS)
- pnpm as package manager
Key Features
Internationalization (i18n)
- Full i18n support with next-intl
- Locale-based routing:
/[locale]/...structure - Supported locales:
en-US(default) andzh-CN - Content organized by locale in
content/[locale]/ - Translation files in
messages/[locale].json
Content Management
- MDX-based blog posts with front matter
- Content processing pipeline:
gray-matterfor front matter parsingnext-mdx-remotefor server-side MDX renderingremarkplugins: gfm, math, directives, gemoji, githubrehypeplugins: slug, autolink-headings, external-links, katex, mdx-code-props
- Rich features: KaTeX math, admonitions, syntax highlighting with Shiki, live code editor with Sandpack
Component Architecture
- Server components by default (Next.js App Router)
- Client components marked with
'use client'when needed - Shadcn UI components in
src/components/ui/(do not modify) - Custom MDX components configured in
src/components/post-content.tsx - Path aliases:
@/forsrc/,@/images/forpublic/images/,@/tests/for__tests__/
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 · 195 lines · 1,670 tokens per session scan A 4460935e3ac9
blog AGENTS.md is an instructions file published in the GitHub repository sabertaz/blog (55 stars, last pushed 29d ago), licensed MIT. It adds 1,670 tokens to every session, about $0.0083 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 instructions, from other repositories
cloudflare-docs AGENTS.md
AGENTS.md instructions for cloudflare/cloudflare-docs, covering agents.md — cloudflare docs, repository overview, directory structure, content — writing and editing docs and file locations.
cloudflare-docs GEMINI.md
Gemini CLI instructions for cloudflare/cloudflare-docs, a project described as: Cloudflare’s documentation.
karngyan.com CLAUDE.md
Instructions for karngyan/karngyan.com, covering claude.md, commands, architecture, conventions and recipes.
easonchang.com-next AGENTS.md
AGENTS.md instructions for eason-dev/easonchang.com-next, covering agents.md — guide for ai coding agents, commands, architecture and conventions.
easonchang.com-next CLAUDE.md
Claude Code instructions for eason-dev/easonchang.com-next, covering claude-specific guidance, skills, hard rules and definition of done.
quireink CLAUDE.md
Claude Code instructions for joiha-steven/quireink, covering quire ink, verify, read first, debug router — a symptom, and the files to open first and hard rules — each one is a bug that already shipped.