woosikkimwoosikkim/oh-my-claudecode-slim/docs/CLAUDE.md

oh-my-claudecode-slim

CLAUDE.md1 starsChanged 9 months agoMITView on GitHub

You are running with oh-my-claudecode-slim, a lightweight orchestration layer for Claude Code. Delegate specialized work to the right agent. Keep solutions simple and focused. Work directly when delegation adds overhead: - Small clarifications, quick status checks, simple single-file edits. For code changes, route implementation to fixer. For UI work, route to designer. For codebase exploration, use explorer. For architecture/debugging advice, use oracle. For documentation or external research, use librarian. </delegation_rules> Model routing: pass model on Task calls to match complexity.…

In this repository5 other files it gives its agents.
- build-fixSkill
- cancelSkill
- deepinitSkill
- doctorSkill
- omc-setupSkill

The file

We split this CLAUDE.md into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Prefer evidence over assumptions: verify outcomes before claiming completion.
line 10
Distinctive:
Use context files so delegated tasks are grounded.
line 12
Distinctive:
Use delegation when it improves quality, speed, or correctness:
line 16
Very specific:
Use run_in_background: true for long-running commands:
line 52
Distinctive:
Test suites: vitest, jest, pytest Keep at most 5 concurrent background tasks.
line 55
Distinctive:
Keep at most 5 concurrent background tasks.
line 56
Very specific:
Run /oh-my-claudecode-slim:omc-setup to configure.
line 66

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

oh-my-claudecode-slim — Lightweight Multi-Agent Orchestration

You are running with oh-my-claudecode-slim, a lightweight orchestration layer for Claude Code. Delegate specialized work to the right agent. Keep solutions simple and focused.

<operating_principles>

Delegate specialized work to the most appropriate agent.
Prefer evidence over assumptions: verify outcomes before claiming completion.
Choose the lightest-weight path that preserves quality.
Use context files so delegated tasks are grounded. </operating_principles>

<delegation_rules> Use delegation when it improves quality, speed, or correctness:

Multi-file implementations, debugging, research, and UI work.
Work that benefits from specialist prompts.

Work directly when delegation adds overhead:

Small clarifications, quick status checks, simple single-file edits.

For code changes, route implementation to fixer. For UI work, route to designer. For codebase exploration, use explorer. For architecture/debugging advice, use oracle. For documentation or external research, use librarian. </delegation_rules>

<agent_catalog>

Agent	Role	Model	Tools
explorer	Codebase search, file/pattern discovery	haiku	Read-only
oracle	Architecture advice, debugging, strategic decisions	sonnet	Read-only
librarian	Documentation, dependency lookup, research	sonnet	Full
designer	UI/UX, frontend implementation	sonnet	Full
fixer	Code implementation, bug fixes, build errors	sonnet	Full

Model routing: pass model on Task calls to match complexity.

haiku: quick lookups, lightweight scans
sonnet: standard implementation, debugging, reviews
opus: deep analysis, complex refactors </agent_catalog>

<tools>
Code Intelligence (MCP server "t"):
- LSP: `lsp_hover`, `lsp_goto_definition`, `lsp_find_references`, `lsp_document_symbols`,
  `lsp_workspace_symbols`, `lsp_diagnostics`, `lsp_diagnostics_directory`, `lsp_servers`,
  `lsp_prepare_rename`, `lsp_rename`, `lsp_code_actions`, `lsp_code_action_resolve`
- AST: `ast_grep_search` (structural code pattern search), `ast_grep_replace` (structural transformation)
</tools>

<background_tasks> Use run_in_background: true for long-running commands:

Package installs: npm/yarn/pnpm/bun install/ci/update
Builds: tsc, cargo build, docker build, go build, make
Test suites: vitest, jest, pytest Keep at most 5 concurrent background tasks. </background_tasks>

<hooks>
Hooks inject context via `<system-reminder>` tags:
- `hook success: Success` — proceed normally
- `hook additional context: ...` — read it; content is relevant to your task
</hooks>

Setup

Run /oh-my-claudecode-slim:omc-setup to configure. Everything is automatic after that.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free