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/geek-fun/serverlessinsight/agents-mdgit clone --depth 1 https://github.com/geek-fun/serverlessinsightWhat 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 | $0.05513 | $0.05513 |
| Opus 5 | $0.02756 | $0.02756 |
| Sonnet 5 | $0.01103 | $0.01103 |
| Haiku 4.5 | $0.00551 | $0.00551 |
Grade A, and why
serverlessinsight 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 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.
How it starts
The opening of the file, as written. The whole thing — 797 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Coding Conventions for AI Agents
This document defines coding conventions that AI agents (and human developers) must follow when contributing to ServerlessInsight.
Build/Lint/Test Commands
# Build the project
npm run build
# Lint check (without fixing)
npm run lint:check
# Lint and auto-fix issues
npm run lint:fix
# Run all tests
npm test
# Run tests for a specific file pattern
npm test -- --testPathPatterns="fc3Resource" --passWithNoTests
# Run a single test file
npm test -- --testPathPatterns="path/to/test.test.ts" --passWithNoTests
# Run tests matching a test name pattern
npm test -- --testNamePattern="should create resource" --passWithNoTests
# CI test run (no debug output)
npm run test:ci
Internationalization (i18n) - MANDATORY
All user-facing messages MUST use the i18n system. Never hardcode English strings.
Pattern
-
Add the message key to
src/lang/en.ts:YOUR_MESSAGE_KEY: 'Your message with {{variable}} placeholder', -
Add the Chinese translation to
src/lang/zh-CN.ts:YOUR_MESSAGE_KEY: '带有 {{variable}} 占位符的中文消息', -
Use the message in code:
import { lang } from '../../lang'; throw new Error(lang.__('YOUR_MESSAGE_KEY', { variable: value }));
Examples
WRONG - Hardcoded English string:
throw new Error(`RAM role "${roleName}" does not exist in the cloud provider.`);
CORRECT - Using i18n:
import { lang } from '../../lang';
throw new Error(lang.__('RAM_ROLE_NOT_FOUND_IN_CLOUD', { roleName }));
Where this applies
- Error messages
- Warning messages
- Info/log messages
- User prompts
- Any text that could be seen by an end user
Where this does NOT apply
- Internal debug identifiers
- API request/response field names
- Code comments
- Variable/function names
Functional TypeScript
Function Style
- Define functions as
const: Useconst xxx = (...) => ...syntax - Prefer functional decomposition over OOP: Avoid classes unless strictly necessary
- Keep functions small and focused: Single responsibility, easy to test
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.
- 2d ago First seen · 797 lines · 5,513 tokens per session scan A 964aad9a04de
serverlessinsight AGENTS.md is an instructions file published in the GitHub repository geek-fun/serverlessinsight (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 5,513 tokens to every session, about $0.0276 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
trigger.dev AGENTS.md
AGENTS.md instructions for triggerdotdev/trigger.dev, covering agents.md, build and development commands, build packages (required before running), verifying changes and apps and internal packages — use typecheck.
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
trigger.dev copilot-instructions.md
Copilot instructions for triggerdotdev/trigger.dev: This is the repo for Trigger.dev, a background jobs platform written in TypeScript. Our webapp at apps/webapp is a Remix 2.1 app that uses Node.js v20. Our SDK is an isomorphic TypeScript SDK at packages/trigger-sdk. Always prefer using isomorphic code like fetch…
microfeed AGENTS.md
AGENTS.md instructions for microfeed/microfeed, covering repository guidance, development workflow, instance management and cloudflare deployment, source architecture and theme repositories.
agent-skills AGENTS.md
Instructions for pulumi/agent-skills, covering pulumi agent skills, repository structure, migration plugin (migration/), pulumi plugin (pulumi/) and package maintenance plugin (package-maintenance/).