build-fix
01Command Claude Code
Run the build, parse errors, and fix them one at a time with minimal changes.
This repository also configures its own agents. See what ai-praxis tells them →
Command Claude Code
Run the build, parse errors, and fix them one at a time with minimal changes.
Command Claude Code
Investigate and fix a bug using a structured debugging methodology.
Command Claude Code
Analyze recent Claude Code conversation transcripts to identify friction points, missing docs, skill gaps, and behavioral corrections.
Command Claude Code
You are the orchestrator. Your job is to stay thin, preserve context, and delegate all heavy lifting to sub-agents. NEVER do deep file reading, code analysis, or implementation directly — always spawn agents for that.
Command Claude Code
Break down a feature request into an actionable implementation plan.
Command Claude Code
Detect and safely remove dead code, unused dependencies, and duplicates.
Command Claude Code
Perform a thorough code review of recent changes or specified files.
Command Claude Code
Guide the implementation of a feature using strict TDD methodology.
Command Claude Code
Analyze code coverage, identify gaps, and generate tests to reach target thresholds.
Command Claude Code
Scan documentation for drift from source-of-truth files and update stale sections.
Command Claude Code
Run a comprehensive verification loop before creating a PR or committing.
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: