Agent Claude Code
Use this agent for strategic product decisions, competitive positioning, developer experience critique, go-to-market strategy, and feature viability assessment. Peer to technical-architect — brings market lens where TA brings system lens. Does NOT write code or create PRs. Advisory only — delegates implementation to…
Agent Claude Code
Use this agent when you need to implement features, fix bugs, or write code anywhere in the Code Insights monorepo. This includes CLI commands, dashboard components (Vite + React SPA), Hono server routes, SQLite schema changes, provider implementations, LLM provider integration, UI work with shadcn/ui, and any…
Agent Claude Code
Use this agent to capture pivotal learning moments, breakthroughs, course corrections, and insights during development. Invoke when detecting learning signals like "I just realized...", "Turns out...", "That didn't work because...", or when a debugging breakthrough or process innovation occurs.
Agent Claude Code
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, cost optimization, or evaluating LLM-generated output quality. Also use when designing new LLM-powered features…
Agent Claude Code
Use this agent for product development coordination, tracking tasks (GitHub Issues or local markdown), sprint planning, progress reporting, and development ceremony management. This PM does NOT use Jira.
Agent Claude Code
Use this agent for architectural decisions, type alignment, SQLite schema changes, code review synthesis, and when the implementation path requires architectural guidance. This agent serves as the technical authority across the Code Insights monorepo. Examples: Context: A change to types needs to be reflected in the…
Agent Claude Code
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, charts). This agent both designs and implements — no handoff needed. Examples: Context: The user wants to improve the…
Command Claude Code
Command "release" from melagiri/code-insights, covering /release — automated release workflow, step 1: pre-flight checks, must be on master, must have clean working tree and pull latest.
Command Claude Code
Command "start-feature" from melagiri/code-insights, covering /start-feature — auto-setup feature development team, step 1: create git worktree, example (adapt the slug from $arguments), step 2: create named team and step 3: spawn pm agent.
Command Claude Code
Command "start-review" from melagiri/code-insights, covering /start-review — triple-layer code review team, step 1: get pr details, get the correct owner from git remote, step 2: select domain specialists and domain classification.
Instructions file
Instructions for melagiri/code-insights, covering claude.md — code insights, project overview, development philosophy (critical), configuration hierarchy and documentation index.