oh-my-claudeagent / templates
AGENTS.md3 starsChanged 32 days agoMITView on GitHub
templates/claudemd.md is the orchestration guidance OMCA's server delivers. The server's guidance handler (servers/hooks/guidance.ts) reads it once per server process from CLAUDE_PLUGIN_ROOT and adds it, with a Session <session_id> line, to the first prompt of each session; the SessionStart handler for compact adds it again after compaction. Nothing writes it into ~/.claude/CLAUDE.md. Editing the template changes what every session receives on its next server start. Keep the text free of anything that varies per session, so the first request's prompt cache…
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hooks/AGENTS.mdAGENTS.md
- opencode/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- servers/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- statusline/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- analyzerSkill
- build-fixerSkill
- consolidate-memorySkill
- debuggingSkill
- github-triageSkill
- git-masterSkill
- handoffSkill
- init-deepSkill
- omca-setupSkill
- planSkill
- refactorSkill
- remove-ai-slopsSkill
- reviewerSkill
- start-workSkill
The file
Files
Template inventory
templates/claudemd.md is the orchestration guidance OMCA's server delivers. The server's
guidance handler (servers/hooks/guidance.ts) reads it once per server process from
CLAUDE_PLUGIN_ROOT and adds it, with a Session <session_id> line, to the first prompt of
each session; the SessionStart handler for compact adds it again after compaction. Nothing
writes it into ~/.claude/CLAUDE.md.
Editing the template changes what every session receives on its next server start. Keep the text free of anything that varies per session, so the first request's prompt cache stays warm.
The always-on per-turn discipline lives separately in output-styles/omca-default.md as a
platform output style; the template carries the operational guidance (entrypoints, agent
catalog, workflow, cross-cutting policy).
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.