melagiri/code-insights
Turn your AI coding sessions into knowledge.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit melagiri/code-insights/.claude ./rig-code-insights # inspect, then merge into .claude/ 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.
$ curl -fsSL --create-dirs -o .claude/agents/devtools-cofounder.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/devtools-cofounder.md $ curl -fsSL --create-dirs -o .claude/agents/engineer.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/engineer.md $ curl -fsSL --create-dirs -o .claude/agents/journey-chronicler.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/journey-chronicler.md $ curl -fsSL --create-dirs -o .claude/agents/llm-expert.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/llm-expert.md $ curl -fsSL --create-dirs -o .claude/agents/product-manager.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/product-manager.md $ curl -fsSL --create-dirs -o .claude/agents/technical-architect.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/technical-architect.md $ curl -fsSL --create-dirs -o .claude/agents/ux-engineer.md https://raw.githubusercontent.com/melagiri/code-insights/master/.claude/agents/ux-engineer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Subagents (7)
| devtools-cofounder model: opus | | |
| engineer model: sonnet | | |
| journey-chronicler model: opus | | |
| llm-expert model: inherit | Use this agent when reviewing, designing, or optimizing any LLM integration — prompts, system prompts, structured output schemas, token budgets, model selection, streaming strategies, rate limiting, c |
| product-manager model: sonnet | | |
| technical-architect model: opus | | |
| ux-engineer model: opus | Use this agent when the task involves UX design work (wireframes, user flows, personas, screen specs) OR building/improving user-facing UI components (chat interfaces, data visualizations, dashboards, |
Slash commands (3)
/release/start-feature/start-review
Similar rigs
aravindhsampath/agentic-template
Cookie-cutter project template for an agentic development workflow: Claude Code architect + engineer subagents, Pi-based multi-model code review (Deepseek + Kimi), strict branch hygiene, declarative apply-standard script.
Pragmatist 2.5k tok ·
kyhsa93/backend-service-playbook
A framework- and language-agnostic guide to DDD-based backend service design, implemented identically across 5 languages (NestJS, Go, Spring Boot Java/Kotlin, FastAPI) with a compliance harness, scaffolding generators, and an AI-agent archi
Pragmatist 6.5k tok ·
jiaheyi-maggie/claude-code-config
Personal Claude Code configuration — commands, hooks, settings, and global instructions
Orchestrator 7.0k tok ·
bijutharakan/multi-agent-squad
Production-ready multi-agent orchestration framework for Claude Code. Features specialized AI agents, automated Git workflows, and comprehensive development automation.
Orchestrator 1.5k tok ·