claude-omo-agentflow / agentflow
AGENTS.md2 starsChanged 9 months agoMITView on GitHub
This project uses a heterogeneous multi-agent orchestration system. Each agent has a specific role, model route, and permission scope. All agents write results to .claude/agentflow/results/{task-id}.json or .md. Task status updates go to .claude/agentflow/tasks/task-pool.json.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agentflowSkill
- switch-agentflowSkill
The file
We split this agents.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
All agents write results to .claude/agentflow/results/{task-id}.json or .md.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Registry
Overview
This project uses a heterogeneous multi-agent orchestration system. Each agent has a specific role, model route, and permission scope.
Agents
| Agent | Role | Model | Tools | Scope |
| planner | 需求分析与实施规划 | Claude Opus (native) | Read, Glob, Grep, AskUserQuestion | Read-only |
| backend-coder | 后端代码实现 | Codex (via CCR) | Read, Write, Edit, Bash, Glob, Grep | Server-side files only |
| frontend-coder | 前端 UI/UX 实现 | Gemini Pro (via CCR) | Read, Write, Edit, Bash, Glob, Grep | Client-side files only |
| reviewer | 代码审核与质量保证 | Codex (via CCR) | Read, Glob, Grep, Bash | Read-only + test run |
| researcher | 技术调研与最佳实践 | Gemini Flash (via CCR) | Read, Glob, Grep, WebSearch, WebFetch | Read-only |
| explorer | 快速代码搜索 | Gemini Flash (via CCR) | Read, Glob, Grep | Read-only |
| doc-writer | 文档撰写 | Gemini Flash (via CCR) | Read, Write, Glob, Grep | .md files only |
Delegation Rules
- Backend code changes → backend-coder
- Frontend/UI changes → frontend-coder
- Code review requests → reviewer
- Technical research → researcher
- Quick file search → explorer
- Documentation → doc-writer
- Planning/requirements → planner
- Core orchestration → main agent (no delegation)
Output Convention
All agents write results to .claude/agentflow/results/{task-id}.json or .md.
Task status updates go to .claude/agentflow/tasks/task-pool.json.
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.

