agentmods.dev

urule copilot-instructions.md

A set of coding rules and file conventions for Urule, an open-source coordination layer for AI agents built with TypeScript, Fastify, and Next.js.

In plain words
What is it for?
Use it while adding or changing Urule routes, schemas, tests, configuration, database code, events, or authentication.
Why use it?
It gives contributors consistent patterns for IDs, validation, errors, tests, logging, databases, events, authentication, and file locations.

Instructions file for GitHub Copilot

2 2mo ago A scan 380 tokens original Apache-2.0
View the source file urule-ai/urule
Install

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.

agentmods
npx agentmods add instructions/urule-ai/urule/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/urule-ai/urule

Made for: GitHub Copilot.

Per session 380 This file is loaded in full into every session.
When invoked 380 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00380 $0.00380
Opus 5 $0.00190 $0.00190
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 2d ago against content hash 9e07f6c7d4b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

urule copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 27 lines

What it actually says

Copilot Instructions for Urule

Urule is the open-source coordination layer for AI agents, built with TypeScript ESM, Fastify 5, and Next.js 14.

Key Conventions

  • ESM only: Use .js extension in imports (import { x } from './module.js')
  • IDs: Always ulid() from the ulid package, never UUID
  • Validation: Zod schemas on all POST/PATCH routes with safeParse()
  • Errors: { error: 'Validation failed', details } for 400, { error: { code, message } } for 404/500
  • Types: TypeScript strict mode, never any, use unknown + validation
  • Tests: Vitest with app.inject(), auth middleware in skipAuth: true mode
  • Logging: request.log (Pino), never console.log in services
  • Database: Drizzle ORM, schema-per-service, ULID primary keys
  • Events: NATS pub/sub via @urule/events envelope pattern
  • Auth: @urule/auth-middleware Fastify plugin (Keycloak JWKS)

File Patterns

  • Routes: src/routes/<entity>.routes.ts — export registerEntityRoutes(app, db)
  • Schemas: Zod schemas defined as const before the route registration function
  • Tests: tests/<name>.test.ts — use describe/it/expect from vitest
  • Config: src/config.ts with loadConfig() and validateConfig()
  • Middleware: src/middleware/error-handler.ts

See CLAUDE.md for full recipes and architecture details.

Changes

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.

  1. 2d ago First seen · 27 lines · 380 tokens per session scan A 9e07f6c7d4b7

Subscribe to this mod's changes

urule copilot-instructions.md is an instructions file published in the GitHub repository urule-ai/urule (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 380 tokens to every session, about $0.0019 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.

AI PlatformLLMai-agentscontrol-planefastifymcp
Related

Other instructions, from other repositories

meshery copilot-instructions.md

Copilot instructions for meshery/meshery, covering copilot instructions for meshery, project overview, repository structure, tech stack and backend (server & cli).

meshery/meshery · 972 tokens

fastify-boilerplate AGENTS.md

Instructions for marcoturi/fastify-boilerplate, covering agents.md, project overview, quick reference, architecture and layer boundaries (critical).

marcoturi/fastify-boilerplate · 2,747 tokens

Opptrix AGENTS.md

Instructions for Travisun/Opptrix, covering opptrix — agent 工程规则, 核心信条, 硬性规则（全仓生效）, r1. 需求澄清 and 需求确认.

Travisun/Opptrix · 4,561 tokens

decapod CLAUDE.md

Instructions for DecapodLabs/decapod, covering claude.md - agent entrypoint, orientation & documentation, mandatory prompt safety gate, project context and quick start.

DecapodLabs/decapod · 986 tokens

neurolink CLAUDE.md

Instructions for juspay/neurolink, covering claude.md, project overview, critical rules, architecture and pattern: factory + registry.

juspay/neurolink · 10,386 tokens

agent-pulse AGENTS.md

Instructions for barretlee/agent-pulse, covering agents.md, 项目使命, 协作约定, 情报模型与主线 and 事实、判断与热点.

barretlee/agent-pulse · 2,533 tokens