Borrowing it
Nothing to install: this file belongs to kinoward/dayu-harness-skill. 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/kinoward/dayu-harness-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/kinoward/dayu-harness-skillWrote 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/kinoward/dayu-harness-skill/agents-md)<a href="https://agentmods.dev/instructions/kinoward/dayu-harness-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kinoward/dayu-harness-skill/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kinoward/dayu-harness-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kinoward/dayu-harness-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04589 | $0.04589 |
| Opus 5.5 | $0.01836 | $0.01836 |
| Sonnet 5.5 | $0.00918 | $0.00918 |
| Haiku 4.5 | $0.00459 | $0.00459 |
Grade A, and why
dayu-harness-skill 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 1mo 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Skill 自身入口。本 Skill 帮助项目建立以 AGENTS.md 为根的渐进式披露文档体系。
目录索引
- AGENTS.md - 当前索引
- SKILL.md - Skill 行为定义
- README.md - 使用者阅读概述与安装指南
- README.en.md - 英文镜像说明文档
- .gitignore - 本仓库临时测试产物忽略规则
- .github/workflows/update-contributors.yml - README 动态区块自动更新工作流
- Q&A-TEMPLATE.md - 初始化与融合问答参考
- LICENSE - MIT 许可文件
- agents/ - Codex UI 与触发策略元数据
- references/agent-compatibility.md - 跨 Agent 兼容说明
- capabilities/ - 治理能力 manifest，部署清单单一事实源
- templates/ - 部署到目标项目的文档模板
- templates.en/ - 英文部署模板镜像树
- assets/ - README 展示资产，以及按能力部署的 hook、CI、配置资产
- marketing/ - 独立对外传播物料，不参与 Skill 功能或部署产物
- scripts/ - Skill 内部环境前置、初始化与安装脚本
- scripts/check-i18n-drift.sh - README 与部署模板镜像漂移检查
- scripts/github-remote.sh - GitHub 远端检查、创建/绑定、推送与远端能力验证脚本
- docs/AGENTS.md - Skill 自身文档入口
- tests/ - Skill 自身测试和 fixture 项目
- tests/README.md - Skill 自身执行测试基线
- tests/smoke/dayu-harness-profile.sh - local-fast / remote-smoke / remote-release 分层测试入口
目录索引变化时，必须同步更新本区块。README 面向使用者，不维护完整仓库目录树；如目录变化影响使用方式或对外说明，再同步更新 README.md 的简版介绍。
Skill 定位
Dayu Harness Skill 面向 Harness Engineering 风格的项目治理：人类定义约束，智能体执行任务，脚本检查结果，仓库沉淀长期记录。
本 Skill 不是目标项目的长期运行时服务。它是一次性部署、融合、诊断、维护和生成入口；长期真相位于目标项目内的 AGENTS.md、docs/、hooks、CI 和维护脚本。
核心转变：
普通 AI 协作：人类在对话里反复提醒 Agent
Dayu Harness：人类把约束写入仓库 -> Agent 读取地图 -> 脚本检查结果 -> 经验回写项目
核心观念
-
Project-centric，而不是 Agent-centric
Skill 只负责部署和升级。长期生效的是目标项目中的
AGENTS.md、docs/、hooks、CI 和脚本。 -
AGENTS.md 优先承担项目地图职责
根索引负责路由和维护事实，子目录索引提供局部上下文，具体指南和传感器脚本承担执行约束。
-
能力清单是单一事实源
capabilities/*.json定义能力 ID、依赖、模板、资产、installer、安全策略和验收标准。
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.
- 1mo ago First seen · 301 lines · 4,589 tokens per session scan A 1249015b4728
dayu-harness-skill AGENTS.md is an instructions file published in the GitHub repository kinoward/dayu-harness-skill (19 stars, last pushed 4mo ago), licensed MIT. It adds 4,589 tokens to every session, about $0.0184 per session on Opus 5.5. 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
ai-agent-rules-generator ui-design.instructions.md
Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).