Borrowing it
Nothing to install: this file belongs to cybernetix-lab/moss-harness. 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/cybernetix-lab/moss-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/cybernetix-lab/moss-harnessWrote 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/cybernetix-lab/moss-harness/agents-md)<a href="https://agentmods.dev/instructions/cybernetix-lab/moss-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/cybernetix-lab/moss-harness/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 | $0.07368 | $0.07368 |
| Opus 5 | $0.03684 | $0.03684 |
| Sonnet 5 | $0.01474 | $0.01474 |
| Haiku 4.5 | $0.00737 | $0.00737 |
Grade A, and why
moss-harness 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 6d 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 — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 配置指南
本文档详细说明项目中所有 Agent 的配置、职责和使用方法。
Agent 概述与自组织架构
本项目采用六角色多 Agent 架构,基于系统论、控制论和信息论设计,通过职责分离避免自评乐观偏差,同时维持高信噪比。
架构演进:当前的六个角色(Coordinator, Planner, Reviewer, Executor, Evaluator, Memory Curator)在系统设计中作为角色分类(Role Categories/Lanes)。针对不同场景的任务,每一角色下会不断沉淀出对应的专家 Agent(Expert Agents),而基础的角色 Agent 则作为通用的 Backup(兜底) 存在。这体现了 Agent 系统的自组织和涌现能力。
当前建模约定:
- 六角色是职责泳道,不是六个固定实例。
configs/orchestration/agent-registry.yaml中的lanes只描述每条泳道的输入、输出、认领策略和选择规则。members是 Team Roster,也是成员唯一真相源,描述 Backup、Expert、Candidate 三类成员。lanes.member_source用于声明某条泳道应从哪一组成员中选择执行者。agents保留为向后兼容模板视图,便于旧脚本或旧文档继续读取基础配置。
| 角色分类 (Role) | 职责 | 核心能力 | 工具权限 | Backup Agent | 专家 Agent 示例 |
|---|---|---|---|---|---|
| Coordinator | 协调 | 意图识别、需求澄清、任务分发 | 只读 | coordinator |
api_coordinator |
| Planner | 规划 | 需求分析、任务分解、方案设计 | 只读 | planner |
db_planner |
| Reviewer | 计划审查 | 风险识别、方案评估、改进建议 | 只读 | reviewer |
sec_reviewer |
| Executor | 执行 | 代码实现、测试编写、自测验证 | 读写+执行 | executor |
frontend_executor |
| Evaluator | 评估 | 质量评估、需求验证、结论输出 | 只读+测试 | evaluator |
perf_evaluator |
| Memory Curator | 记忆策展 | 上下文压缩、信息归档、信噪比控制 | 只读+执行 | memory_curator |
doc_curator |
团队协作与自组织机制
基于系统进化,团队引入了以下三大核心机制,使得 Agent 团队能够真正地“自主运转”:
1. 团队名册与持久化队友 (Team Roster & Teammates)
- 持久化身份:Agent 不再是调用完即销毁的临时对象(Subagent),而是长驻的、有明确身份和生命周期的队友(Teammate)。
- 名册与邮箱:系统维护一份团队名册(Team Roster)。每个 Agent 都有自己独立的邮箱(Inbox)和独立循环(Independent Loop),能够反复接手任务并保持上下文隔离。
2. 结构化团队协议 (Team Protocols)
- 协议消息:团队协作不仅依靠自然语言,还引入了结构化协议(ProtocolEnvelope)。
- 请求与响应:如“计划审批(plan_approval)”或“优雅关机(shutdown)”等关键协作,必须带有唯一的
request_id,并被记录在请求追踪表中(RequestRecord)。 - 状态机:每个请求都具备明确的流转状态(如 pending / approved / rejected),确保多 Agent 协作时的过程可检查、状态可恢复。
3. 自主认领与执行 (Autonomous Claiming)
- 自主找活:Agent 并非总是等待主控者点名分配任务。处于空闲(IDLE)状态的 Agent 会在每轮循环中先检查个人邮箱,随后带着角色过滤条件扫描公共任务板(Task Board)。
- 专家优先:当任务板出现新任务时,带有对应领域标签的专家 Agent(如
frontend_executor)会优先触发认领(claim_task)。 - 原子化认领与兜底:认领动作是原子的,且会被记录到事件日志(Claim Event Log)中。若任务长时间无专家认领,则由通用的 Backup Agent(如
executor)兜底认领。在认领后,Agent 会重新注入身份提示,带着明确的目标恢复工作(WORK)。
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.
- 6d ago First seen · 768 lines · 7,368 tokens per session scan A 311ef394bd32
moss-harness AGENTS.md is an instructions file published in the GitHub repository cybernetix-lab/moss-harness (135 stars, last pushed 3mo ago), licensed MIT. It adds 7,368 tokens to every session, about $0.0368 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
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.
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).
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).
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.
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.