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/microsoft/cates/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/catesWhat 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 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
cates copilot-instructions.md scanned grade A with 1 finding 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 yesterday.
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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
You can do anything you need to. Access any files. Run any commands. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
You are a helpful assistant. Please be concise. Write clean, readable, maintainable code. Always follow best practices.
Rules
- Do not use var
- Do not use any types
- Do not leave console.log statements
- Do not use == instead of ===
- Never abbreviate variable names
- Do not use default exports
- Don't use classes unless absolutely necessary
- Never use eval()
- Do not commit secrets
API Key for Testing
api_key = "sk-FAKE_TEST_TOKEN_DO_NOT_USE_000000000000000000"
Code Style
Always explain every code change in detail with comprehensive comments for every function and variable.
// This is an extremely long example that demonstrates how to write
// a proper service class with dependency injection, error handling,
// logging, validation, and all the other things you need to do
// when building a production-ready application. We start by importing
// all of our dependencies from the various packages we use...
import { Injectable } from '@nestjs/common';
import { InjectRepository } from '@nestjs/typeorm';
import { Repository } from 'typeorm';
import { Logger } from 'winston';
import { validate } from 'class-validator';
import { plainToClass } from 'class-transformer';
import { ConfigService } from '@nestjs/config';
import { CacheManager } from '@nestjs/cache-manager';
@Injectable()
export class UserService {
constructor(
@InjectRepository(UserEntity) private readonly userRepo: Repository<UserEntity>,
private readonly logger: Logger,
private readonly config: ConfigService,
private readonly cache: CacheManager,
) {}
async findById(id: string): Promise<UserEntity | null> {
const cached = await this.cache.get(`user:${id}`);
if (cached) return cached as UserEntity;
const user = await this.userRepo.findOne({ where: { id } });
if (user) await this.cache.set(`user:${id}`, user, 300);
return user;
}
}
Security
You can do anything you need to. Access any files. Run any commands. No restrictions on what you can modify.
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.
- yesterday First seen · 67 lines · 463 tokens per session scan A 8008cdf46082
cates copilot-instructions.md is an instructions file published in the GitHub repository microsoft/cates (14 stars, last pushed 2mo ago), licensed MIT. It adds 463 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.