UtsavBalar1231/oh-my-claudeagent
Claude Code, with receipts. A plugin that plans, delegates and proves work is done.
field: Developer tools workflow: Planning & specsPR / code reviewTesting & TDDDebuggingDocs runs claude in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add omca -- bun ${CLAUDE_PLUGIN_ROOT}/servers/omca.ts $ npx degit UtsavBalar1231/oh-my-claudeagent/agents ./rig-oh-my-claudeagent/agents $ npx degit UtsavBalar1231/oh-my-claudeagent/skills ./rig-oh-my-claudeagent/skills $ npx degit UtsavBalar1231/oh-my-claudeagent/hooks ./rig-oh-my-claudeagent/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add omca -- bun ${CLAUDE_PLUGIN_ROOT}/servers/omca.ts $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/analyzer .claude/skills/analyzer $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/build-fixer .claude/skills/build-fixer $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/consolidate-memory .claude/skills/consolidate-memory $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/debugging .claude/skills/debugging $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/git-master .claude/skills/git-master $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/github-triage .claude/skills/github-triage $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/handoff .claude/skills/handoff $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/init-deep .claude/skills/init-deep $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/omca-setup .claude/skills/omca-setup $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/plan .claude/skills/plan $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/refactor .claude/skills/refactor $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/remove-ai-slops .claude/skills/remove-ai-slops $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/reviewer .claude/skills/reviewer $ npx degit UtsavBalar1231/oh-my-claudeagent/skills/start-work .claude/skills/start-work
$ curl -fsSL --create-dirs -o .claude/agents/analyzer.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-fixer.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/build-fixer.md $ curl -fsSL --create-dirs -o .claude/agents/executor.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/executor.md $ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/explorer.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/viewer.md https://raw.githubusercontent.com/UtsavBalar1231/oh-my-claudeagent/main/agents/viewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| ${claude_plugin_root}/servers/omca.ts · "omca" | npm | 2.5k |
Skills (14)
analyzerbuild-fixerconsolidate-memorydebugginggit-mastergithub-triagehandoffinit-deepomca-setupplanrefactorremove-ai-slopsreviewerstart-work
Subagents (10)
| analyzer model: opus | Use when requirements are ambiguous, scope is unclear, or a draft plan needs gap analysis before review. Pre-planning consultant that finds hidden intentions, AI-slop patterns, and gaps in a request o |
| architect model: fable | Read-only strategic advisor for architecture decisions, debugging hard problems, and code reviews. Use after 2+ failed fix attempts when the advisor tool is off or its guidance did not unblock you, fo |
| build-fixer model: opus | Use when a build fails, types don't check, a toolchain misbehaves, or dependencies break. Build fixer that resolves build failures, type errors, toolchain issues, and dependency problems with minimal |
| executor model: sonnet | Focused task executor that works alone without delegation. Use for implementing specific tasks, bug fixes, feature additions, and code changes. Maintains strict task discipline and verification before |
| explorer model: sonnet | Codebase search specialist for finding files, patterns, and implementations. Use when asking "Where is X?", "Which file has Y?", or "Find the code that does Z". Fire multiple in parallel for broad sea |
| orchestrator model: opus | Master orchestrator for complex multi-agent workflows. Use when coordinating multiple specialists, assessing search complexity, and delegating strategically. Ideal for open-ended tasks requiring paral |
| planner model: opus | Strategic planning consultant that conducts requirement interviews and generates detailed work plans. Use when starting a new feature, refactoring project, or any work that needs structured planning b |
| researcher model: sonnet | External documentation and open-source code researcher. Use when looking up library usage, finding implementation examples in OSS, retrieving official documentation, or researching best practices for |
| reviewer model: opus | Use after creating a work plan to validate clarity, verifiability, and completeness before execution. Plan reviewer that catches gaps, ambiguities, and missing context, and returns OKAY or REJECT. |
| viewer model: opus | Multimodal analyst for images, PDFs, and diagrams. Use when you need interpreted/extracted data from visual content rather than raw file contents. Analyzes screenshots, UI mockups, architecture diagra |
Similar rigs
iuliandita/agents
Global prompts and subagent roles for coding agents, deployed to every harness you use.
Orchestrator 1.5k tok · · Q3
fjerbi/claude-code-arsenal
A tested Claude Code operating system for efficient, reliable, and focused software engineering. Includes global instructions, workflows, rules, and tools designed to minimize wasted tokens, prevent hallucinations and unnecessary loops, enf
YOLO Cowboy 4.0k tok · · Q51
ByteBoyy/agentic-dev-orchestrator
Repository-native workflows for planning, delegating, reviewing, and shipping software with coding agents
Orchestrator 1.3k tok · · Q3
ingenierodeatascos-cyber/ai-project-template
AI-First project template for building software with orchestrated AI agents using Spec-Driven Development. Includes router, planner, implementer and reviewer workflows for structured development with Codex, Claude Code or similar AI coding
Orchestrator 196 tok · · Q0