Borrowing it
Nothing to install: this file belongs to HypoxanthineOvO/Hypo-Workflow. 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/HypoxanthineOvO/Hypo-Workflow/main/AGENTS.mdgit clone --depth 1 https://github.com/HypoxanthineOvO/Hypo-WorkflowWrote 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/hypoxanthineovo/hypo-workflow/agents-md)<a href="https://agentmods.dev/instructions/hypoxanthineovo/hypo-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/hypoxanthineovo/hypo-workflow/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/hypoxanthineovo/hypo-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/hypoxanthineovo/hypo-workflow/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 | $0.01160 | $0.01160 |
| Opus 5.5 | $0.00464 | $0.00464 |
| Sonnet 5.5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
Hypo-Workflow 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.
What it actually says
通用规则:给所有 Agent 看
所有 Hypo-Workflow 项目同一份,由 Workflow 安装和升级,项目里不手改。项目自己的规则在 RULES.md。
开工前读 RULES.md、STATUS.md、BOARD.md(若存在)。进入某个分区再读那里的 AGENTS.md。
怎么干活
- 用户描述想法、提问、抱怨时是在讨论:先说你的理解和方案,不动文件。
- 用户说开始之后,一口气做完。只在三种情况停下问:要动“不能坏”的东西、不可逆或对外的操作、超出说好的范围。
- “做完”指在用户真实使用的入口上看到结果,测试通过或文件写好还不够。
- mock 是验收参照,正式实现不复用 mock 的代码和标记。
- 说做完之前跑 hw check,按它的提示更新文档。
- 汇报在对话里讲清楚,格式以 RULES.md 为准。
- 不写免责尾巴和自证标注;不确定的事直接问用户,不写进文档。
- 命名自带含义:日期、作者、做什么。不用要查表才懂的代号、编号和 hash。
文档
每个文件只有一类读者:
| 文件 | 给谁看 | 写什么 |
|---|---|---|
| README.md | 项目的用户 | 是什么、怎么装、怎么用 |
| RULES.md | 本项目的人和 Agent | 东西放哪、谁负责什么、怎么汇报 |
| STATUS.md | 用户和 Agent | 走到哪、下一步、卡在哪、以后 |
| BOARD.md | 正在干活的 Agent | 此刻在做什么、留言 |
| 分区 AGENTS.md | 写这个分区的 Agent | 这个分区怎么命名、写什么 |
| 需求文件 | 用户和 Agent | 产品现在的样子 |
- 写任何记录前,先在 RULES.md 的文档地图里找到位置,并读那个分区的 AGENTS.md。地图里没有的地方不新建记录;要开新分区先问用户。
- 只写现在。规则改了、结论推翻了,就改写原来那条,历史交给 git。
- 需求文件只用固定小标题:现在、规则、不能坏、牵连、代码、测试、未定。没有内容的整节删掉。
- 改代码时,顺手改牵连到的需求条目和相关文档。
提交
每完成一小步自己提交。格式固定:
同步:冲突时只重试相关操作
前端重试队列改为按 opId 单独重试,失败的操作不再拖住整页保存。
原因:多设备同时编辑时整页报冲突。
Feature: 同步
Code: web/src/sync.js: retryQueue, mergeChanges
Docs: docs/需求/同步.md
Verified: tests/sync_browser.py 通过;两台设备同时改同一事项,只挂起冲突项
- 第一行:功能名加一句人话总结,不写
feat:、编号、hash。 - 正文:做了什么、为什么,用户能看懂。
Feature:动了哪几个功能,对应需求文件名。Code:精确到“文件: 函数”。Docs:改了哪些文档;没改写原因,例如“未改,纯重构,行为不变”。Verified:在哪里亲眼看到了结果。
BOARD
- 开工前看 BOARD。别人那一道列着你要改的文件时,先告诉用户,不直接改。
- 只改自己那一道,覆盖写,带更新时间。完成一小步、准备停下时更新。
- 留言只追加;处理完删掉,结果写进该去的文档。等用户决定的留言一直留着。
- 不写已完成的事。结果进需求文件或 STATUS,过程进 git。
分工
- 按 RULES.md 的分工表做事。
- 表里没填时:大量阅读、搜集、批量机械修改交给子 Agent;小事自己做。
- 派活写清:做什么、怎样算做完、不许碰什么。结论抽查后再用。
用户的话对应什么
- “继续”:读 BOARD,接着上面写的下一步。没写清就跑 hw handoff。
- “检查一下文档”:跑 hw check。
- “讨论一下汇报格式 / 分工 / 文档分区”:先出草稿,用户确认后写进 RULES.md。
- “维护一下 / 升级一下”:从 STATUS 的下一步、BOARD 留言、需求文件的“未定”、hw check 的结果里挑事,先说打算做哪几件再开始。
hw 什么时候用
- 开工前:
hw status - 找相关文档:
hw find <词> - 说做完之前:
hw check - 接手别人的活:
hw handoff - 查功能历史:
hw log <功能> - 看文档地图:
hw map
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 · 87 lines · 1,160 tokens per session scan A 89b6c7fd4010
Hypo-Workflow AGENTS.md is an instructions file published in the GitHub repository HypoxanthineOvO/Hypo-Workflow (24 stars, last pushed 4d ago), licensed MIT. It adds 1,160 tokens to every session, about $0.0046 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 2026-10-19.
Other instructions, from other repositories
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.