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/krahets/krahets.github.io/claude-mdgit clone --depth 1 https://github.com/krahets/krahets.github.ioWrote 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/krahets/krahets.github.io/claude-md)<a href="https://agentmods.dev/instructions/krahets/krahets.github.io/claude-md"><img src="https://agentmods.dev/badge/instructions/krahets/krahets.github.io/claude-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 | $0.01685 | $0.01685 |
| Opus 5 | $0.00843 | $0.00843 |
| Sonnet 5 | $0.00337 | $0.00337 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
krahets.github.io CLAUDE.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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
krahets.com — Personal Academic Website
Single-page static site for Yudong Jin. Plain HTML + CSS + vanilla JS, no framework, no build step. Deployable directly to Cloudflare Pages.
File Structure
index.html # Entire website — HTML, CSS, and JS in one file
assets/
profile_light.jpg / profile_dark.jpg # Avatar (theme-aware)
favicon.png # Circular favicon (128×128)
pub_4danyone.mp4 # Publication preview video
pub_lingbot_va_v2.mp4 # Publication preview video
pub_pointsplat.mp4 # Publication preview video
pub_scal3r.mp4 # Publication preview video
pub_diffuman4d.mp4 # Publication preview video
pub_envgs.mp4 # Publication preview video
book_hello_algo.jpg # Open-Source section thumbnail
book_illustration.jpg # Open-Source section thumbnail
exp_robbyant.jpg / exp_antgroup.png # Experience card icons
Design System
Colors — OKLCH perceptually uniform color tokens, defined on :root and [data-theme="dark"]:
--bg,--text-primary,--text-secondary,--text-muted— neutrals--accent— blue links--accent-bg,--accent-border— link pill hover fill and border--star-*— GitHub star badge colors--border— dividers
Type scale — Lato (300/400/700 only). Available sizes: --text-xs (12px), --text-sm (14px), --text-base (16px), --text-md (18px), --text-lg (20px). No 500/600 weights — use 400 or 700.
Chinese name — 靳宇栋 uses LXGW WenKai TC (Google Fonts, 400 only).
Spacing — --max-width: 760px, fluid padding with clamp().
Dark Mode
- Toggled via
data-themeattribute on<html> - Anti-flash inline
<script>in<head>readslocalStorageandprefers-color-scheme - JS at bottom of
<body>handles toggle button, avatar swap, and GitHub star count loading - Dark theme images dimmed with
filter: brightness(0.82)on.pub__thumb,.book__thumb,.exp-card__icon
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 · 99 lines · 1,685 tokens per session scan A 643281d9b943
krahets.github.io CLAUDE.md is an instructions file published in the GitHub repository krahets/krahets.github.io (2 stars, last pushed 12d ago), licensed MIT. It adds 1,685 tokens to every session, about $0.0084 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.