Command Claude Code
Run the Spec-First App consistency audit workflow.
Multi-agent code analysis assistant: enter a GitHub repository URL to generate architecture reports traceable to files and line numbers, code reviews, and a queryable index. LangGraph + RAG + MCP + React.
This repository also configures its own agents. See what codepilot-agent tells them →
Command Claude Code
Run the Spec-First App consistency audit workflow.
Command Claude Code
Run the Spec-First brainstorm workflow.
Command Claude Code
Run the Spec-First code review workflow.
Command Claude Code
Refresh stale Spec-First solution docs.
Command Claude Code
Run the Spec-First knowledge capture workflow.
Command Claude Code
Run the Spec-First debug workflow.
Command Claude Code
Run the Spec-First document review workflow.
Command Claude Code
Run autonomous diff-scoped browser dogfood QA for a branch or PR.
Command Claude Code
Run the Spec-First ideation workflow.
Command Claude Code
Run metric-driven iterative optimization loops.
Command Claude Code
Start the dev server and iterate on browser-visible polish.
Command Claude Code
Run the Spec-First PRD requirements workflow.
Command Claude Code
Install, configure, verify, and refresh required harness runtime readiness facts for spec-first workflows.
Command Claude Code
Run the Spec-First execution workflow.
Command Claude Code
Design and author project-owned Agent Skills, or validate packages read-only.
Command Claude Code
Public workflow entrypoint (spec-write-tasks): compile a settled local spec-plan into an optional derived task pack for spec-work, or validate an existing local task pack before execution. Use for explicit plan-splitting/task-doc requests or high-complexity work suitability; do not use for plan authoring…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: