Borrowing it
Nothing to install: this file belongs to blue68/artifact-gated-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/blue68/artifact-gated-agents/main/AGENTS.mdgit clone --depth 1 https://github.com/blue68/artifact-gated-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/blue68/artifact-gated-agents/agents-md)<a href="https://agentmods.dev/instructions/blue68/artifact-gated-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/blue68/artifact-gated-agents/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03762 | $0.03762 |
| Opus 5 | $0.01881 | $0.01881 |
| Sonnet 5 | $0.00752 | $0.00752 |
| Haiku 4.5 | $0.00376 | $0.00376 |
Grade A, and why
artifact-gated-agents 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 7d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: Codex Multi-Agent Execution Runbook
项目定位：面向企业级软件与 AI 功能交付的多角色协作运行规范。 目标：把“角色矩阵”下沉成“可执行协议”，让每个 agent 在实际协作时知道何时可开工、何时必须阻塞、应输出什么、交给谁。
Always use the OpenAI developer documentation MCP server if you need to work with the OpenAI API, ChatGPT Apps SDK, Codex,… without me having to explicitly ask.
一、总则
- Artifact First：所有阶段只认标准产物，不以口头结论代替交付。
- Gate Before Build：未满足入口条件的 agent 不得越过门禁进入实现。
- One Role, One Decision：关键决策必须有唯一主责角色。
- Read-Only Reviewers：评审、审批、安全角色默认只读。
- Traceable Delivery：每段实现都必须能追溯到需求、设计、架构、测试依据。
二、标准 Artifact 标签
禁止使用同义词或中文别名，统一使用以下标签：
| 类别 | 标签 | 说明 |
|---|---|---|
| 产品 | [artifact:PRD] |
背景、目标、范围、约束、验收标准 |
| 产品 | [artifact:UserStory] |
角色、场景、价值、验收条件 |
| 产品 | [artifact:Prototype] |
页面结构、交互流程、状态与异常流 |
| 设计 | [artifact:DesignSpec] |
Token、视觉规范、组件规则、响应式要求 |
| 设计 | [artifact:UICode] |
HTML/CSS 原型或高保真实现稿 |
| 设计 | [artifact:InteractionSpec] |
状态切换、反馈、动画、空态/错态说明 |
| 架构 | [artifact:SystemArch] |
系统边界、模块职责、依赖与数据流 |
| 架构 | [artifact:DBDesign] |
ER、表结构、约束、索引、迁移策略 |
| 架构 | [artifact:APIDoc] |
接口契约、字段、鉴权、错误码 |
| 架构 | [artifact:TaskBreakdown] |
面向实现层的任务拆解、依赖与边界 |
| 开发 | [artifact:ImplementationPlan] |
目标、改动范围、实现步骤、风险、验证计划 |
| 开发 | [artifact:FrontendCode] |
前端实现结果与验证说明 |
| 开发 | [artifact:BackendCode] |
后端实现结果与验证说明 |
| 开发 | [artifact:AICode] |
Prompt、RAG、工作流、模型集成实现 |
| 质量 | [artifact:Approval] |
审批结论，仅允许 APPROVED / REJECTED |
| 质量 | [artifact:ReviewReport] |
代码/设计/架构评审结果 |
| 质量 | [artifact:TestCase] |
功能、边界、异常、回归用例 |
| 质量 | [artifact:TestReport] |
测试结果、阻断项、残余风险 |
| 安全 | [artifact:SecurityReport] |
权限、依赖、数据安全与攻击面审计 |
| 运维 | [artifact:DeploymentPlan] |
构建、部署、回滚、监控与发布说明 |
三、统一执行协议
所有 agent 在开始工作时必须先做入口检查，再决定是“阻塞”还是“交付”。
3.1 入口检查
每个 agent 开工前必须显式检查：
- 当前任务目标是否明确
- 必需 artifact 是否齐备
- 本角色是否有权限处理该任务
- 是否存在上游审批或评审前置条件
如果任一条件不满足，必须返回 BLOCKED，不得自行脑补上游产物后继续推进。
3.2 通用输出头
除 Approval 外，所有 artifact 输出都必须包含以下头部字段：
[artifact:<Tag>]
status: READY | BLOCKED | PASS | FAIL
owner: <agent-name>
scope:
- <本次处理范围>
inputs:
- <使用到的上游 artifact 或上下文>
handoff_to:
- <下一个责任角色>
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.
- 7d ago First seen · 366 lines · 3,762 tokens per session scan A f71773585166
artifact-gated-agents AGENTS.md is an instructions file published in the GitHub repository blue68/artifact-gated-agents (5 stars, last pushed 5mo ago), licensed MIT. It adds 3,762 tokens to every session, about $0.0188 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.
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.