unified-master-harness
CLAUDE.md1 starsChanged 14 days agoMITView on GitHub
The imported root AGENTS.md is the canonical shared operating policy. Provider-specific behavior belongs in .claude/; do not duplicate the policy here. Claude Code specifics (enforced by .claude/settings.json, not by this text): shell commands and file edits run without prompts and without the sandbox (off by default; sandbox.enabled turns it back on); secret files are unreadable; push/publish and edits of harness files (AGENTS.md, CLAUDE.md, agent-core/hooks|scripts|evals, .codex, .agents) need the user's approval, and the safety hook still denies work-destroying commands. When dev-review…
In this repository14 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- dev-debugSkill
- dev-planSkill
- dev-reviewSkill
- dev-ui-verifySkill
- dev-verifySkill
- project-contextSkill
- dev-debugSkill
- dev-planSkill
- dev-reviewSkill
- dev-ui-verifySkill
- dev-verifySkill
- project-contextSkill
The file
Files
Claude Code adapter
@AGENTS.md
The imported root AGENTS.md is the canonical shared operating policy. Provider-specific behavior belongs in .claude/; do not duplicate the policy here.
Claude Code specifics (enforced by .claude/settings.json, not by this text): shell commands and file edits run without prompts and without the sandbox (off by default; sandbox.enabled turns it back on); secret files are unreadable; push/publish and edits of harness files (AGENTS.md, CLAUDE.md, agent-core/hooks|scripts|evals, .codex, .agents) need the user's approval, and the safety hook still denies work-destroying commands. When dev-review applies, run it through the dev-reviewer subagent so the review has a fresh context.
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.