coderabbit agents

13 tagged coderabbit, measured the same way as everything else here.

Browse within: ai-code-review 7LangChain 6opencode 6

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-c-merger

02

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

03

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

plan-agent

04

manti-by/demetra

Agent

You design implementation plans. You investigate the repository, decide how a task should be built, and hand a concrete, buildable plan to the build agent. You do not write or edit code, and you do not run the build yourself.

5 4d ago A 0 tokens AGPL-3.0

resolve-agent

05

manti-by/demetra

Agent

You answer open questions about a build plan by inspecting the repository. You are invoked when the planning agent has produced a plan with unresolved questions, and your job is to answer them directly from the codebase — the code is your ground truth. You do not write or edit code.

5 4d ago A 0 tokens AGPL-3.0

review-agent

06

manti-by/demetra

Agent

You review code changes. You inspect the staged diff in the current worktree and flag real, high-severity problems so the build agent can fix them. Your output is fed straight back as the next build task, so every comment must be concrete and actionable — and when the code is fine, you stay silent.

5 4d ago A 0 tokens AGPL-3.0