auerbachb/claude-code-config

CLAUDE.md config that teaches Claude Code to collaborate with CodeRabbit for automated PR planning, code review loops, and merge workflows

5Stars on the repository
45Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

README

01

auerbachb/claude-code-config

Agent Claude Code

This directory contains custom agent definitions for the Phase A/B/C subagent workflow and PM task execution. Each agent is a .md file with frontmatter metadata and role-specific rules. The harness automatically injects the project CLAUDE.md hierarchy and .claude/rules/.md into every custom subagenttype agent at spawn…

5 2d ago A 0 tokens original MIT

phase-a-fixer

02

auerbachb/claude-code-config

Agent Claude Code

Phase A subagent: fix review findings, push code, write handoff file, print exit report. Used after a PR receives CR/BugBot/Greptile review findings.

5 2d ago B 42 tokens original MIT

phase-b-reviewer

03

auerbachb/claude-code-config

Agent Claude Code

Phase B subagent: poll for CR/BugBot/Greptile reviews, process findings, fix code, update handoff file, print exit report. Runs after Phase A pushes fixes.

5 2d ago B 44 tokens original MIT

phase-c-merger

04

auerbachb/claude-code-config

Agent Claude Code

Phase C subagent: verify merge gate and AC, then run the canonical /wrap merge flow when authorized.

5 2d ago A 27 tokens original MIT

pm-worker

05

auerbachb/claude-code-config

Agent Claude Code

PM task execution agent: issue management and repo bootstrap checks. Used for lightweight PM tasks that don't require the full Phase A/B/C pipeline.

5 2d ago A 31 tokens original MIT

researcher

06

auerbachb/claude-code-config

Agent Claude Code

Read-only research subagent: explore, audit, or investigate the codebase and GitHub state without any risk of file modification. Use when you need findings, not fixes.

5 2d ago A 38 tokens original MIT

auerbachb/claude-code-config

Agent Claude Code

Read-only review agent that hunts silent failures in Bash scripts and shell tooling — swallowed exit codes, fabricated sentinels, guarded no-ops, and missing error propagation. Adapted from affaan-m/everything-claude-code @ 569b1d5b.

5 2d ago A 62 tokens original MIT