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/miantiao-me/cloud-code/agents-mdgit clone --depth 1 https://github.com/miantiao-me/cloud-codeWhat 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 | $0.01921 | $0.01921 |
| Opus 5 | $0.00960 | $0.00960 |
| Sonnet 5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
cloud-code 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Development Guide (AGENTS.md)
1. Project Overview
A TypeScript project based on Cloudflare Workers and Cloudflare Containers (Durable Objects).
Leverages Cloudflare edge infrastructure to run and manage containerized workloads (AgentContainer).
⚠️ Core Principle: All comments, logs, and commit messages MUST be in concise English.
2. Build and Development Commands
2.1 Core Commands
| Command | Description | Notes |
|---|---|---|
pnpm dev |
Start local development server | Equivalent to wrangler dev |
pnpm start |
Alias for pnpm dev |
- |
pnpm deploy |
Deploy to Cloudflare | Equivalent to wrangler deploy |
pnpm cf-typegen |
Generate Cloudflare Bindings types | Must run after modifying wrangler.jsonc |
2.2 Code Quality Commands
| Command | Description | Notes |
|---|---|---|
pnpm lint |
Run oxlint to check code | High-performance Rust linter |
pnpm lint:fix |
Auto-fix lint issues | Equivalent to oxlint --fix |
pnpm fmt |
Format code | Uses oxfmt (Biome fork) |
pnpm fmt:check |
Check formatting compliance | Used in CI, does not modify files |
2.3 About Testing
Important: The repository currently has no test framework (Jest/Vitest).
- Do not attempt to run
pnpm test(command does not exist).- Validation methods: TypeScript compiler (
pnpm cf-typegen) +pnpm lint+ manual code review.- If adding tests, Vitest is recommended (good compatibility with Wrangler).
3. Code Style and Conventions
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 · 181 lines · 1,921 tokens per session scan A df8189e38361
cloud-code AGENTS.md is an instructions file published in the GitHub repository miantiao-me/cloud-code (558 stars, last pushed 7mo ago), licensed MIT. It adds 1,921 tokens to every session, about $0.0096 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
codeg AGENTS.md
Instructions for xintaofei/codeg, covering agents.md, 项目概述, 技术栈, 代码检查与测试（任务完成后进行必要的检查） and 前端.
agent-harness-kit AGENTS.md
Instructions for enmanuelmag/agent-harness-kit, covering agents.md — @cardor/agent-harness-kit, project, health check (run before making codebase changes), harness data (source of truth) and mcp tools (preferred).
open-vibe-island AGENTS.md
AGENTS.md instructions for Octane0411/open-vibe-island, covering agents, goal, required workflow, commit policy and safety rules.
open-vibe-island CLAUDE.md
Claude Code instructions for Octane0411/open-vibe-island, covering claude.md, project, architecture, build & run and dev app (open island dev.app).
codehydra CLAUDE.md
Instructions for stefanhoelzl/codehydra, covering claude.md, critical rules, no ignore comments, api/ipc interface changes and new boundary interfaces.
Unity-Open-MCP AGENTS.md
Instructions for AlexeyPerov/Unity-Open-MCP, covering agent rules, rule scope and precedence, universal contributor rules and maintainer process when specs/ is available.