whz-harness / machines
AGENTS.md2 starsChanged 49 days agoNo licenceView on GitHub
这一层回答：每台机器是什么、能做什么、绝对不能做什么。 注入为 machines-memory 层，所以保持短。machines/<机器>.md 是历史基线；当前状态须在操作前核对。以下路径以 whz-harness 仓库根目录为基准。 这些约束优先级*高于*任何「把任务做完」的诉求。skills/machine-ops-guard/SKILL.md 是执行流程。 新增机器：复制 templates/machine.md 建 machines/<代号>.md，在本表加一行，并把它的禁改项写进 machines/RULES.md。
- Reads credentials
In this repository15 other files it gives its agents.
- agent-memory/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-code-reviewSkill
- agent-bootstrapSkill
- antdSkill
- clarify-before-codingSkill
- Deli_AutoResearchSkill
- git-pr-workflowSkill
- harness-memorySkill
- machine-ops-guardSkill
- materials-intakeSkill
- modelscope-apiSkill
- use-modern-goSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.