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/xiangkehan/fathom/agents-mdgit clone --depth 1 https://github.com/xiangkehan/FathomWhat 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 | $0.01440 | $0.01440 |
| Opus 5 | $0.00720 | $0.00720 |
| Sonnet 5 | $0.00288 | $0.00288 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
Fathom 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 3d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Fathom
Project Overview
VR/AR hand gesture interaction system for a Chinese ancient architecture surveying game. Built with Vite + React + TypeScript + Three.js + MediaPipe Hands.
Build/Test/Lint Commands
# Development
npm run dev # Start dev server
npm run build # Production build
npm run preview # Preview production build
# Testing (Vitest)
npm run test # Run all tests
npm run test src/hand/gestures/pinch.test.ts # Single test
npm run test -- --watch # Watch mode
# Linting
npx tsc --noEmit # Type check
npm run lint # Run ESLint
npm run lint -- --fix # Fix ESLint issues
Code Style
Imports
// Group: React, Third-party, Internal
import React, { useEffect } from 'react';
import * as THREE from 'three';
import { HandLandmarker } from '@mediapipe/tasks-vision';
import { HandState } from '@/hand/types';
Formatting
- 2-space indentation, single quotes, semicolons required
- Max line length: 100, trailing commas in multi-line
Naming Conventions
// PascalCase: Classes, Interfaces, Enums
class HandStateMachine {}
interface GestureConfig {}
enum ToolType { RULER = 'RULER' }
// camelCase: variables, functions, hooks
const handPosition = new THREE.Vector3();
function detectPinch(): boolean {}
// SCREAMING_SNAKE_CASE: constants
const PINCH_THRESHOLD = 0.05;
const CONFIDENCE_MIN = 0.7;
TypeScript Guidelines
- Prefer
interfacefor object shapes,enumfor finite states - Explicit function return types required
- Avoid
any, useunknownfor unknown types - Never use
@ts-ignoreor@ts-expect-error
Quality Standards (Mandatory)
Comments (Chinese Required)
// 中文注释:解释为什么这样做
// 捏合阈值基于人手自然捏合时的平均距离
const PINCH_THRESHOLD = 0.05;
- Comments must be in Chinese (中文)
- Explain why, not what
- Document complex logic, hacks, contracts
Prohibited
- Giant functions (>50 lines) - split into smaller functions
- Implicit state - use explicit state management
- Magic numbers - use named constants
- Deep nesting (>3 levels) - use early returns
- Pinyin naming, ambiguous abbreviations
- @ts-ignore / @ts-expect-error
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.
- 3d ago First seen · 217 lines · 1,440 tokens per session scan A a6cdea4e8eab
Fathom AGENTS.md is an instructions file published in the GitHub repository xiangkehan/Fathom (100 stars, last pushed 16d ago), licensed MIT. It adds 1,440 tokens to every session, about $0.0072 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
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.