Coding Review Agent Loop — Development skill for Claude Code
Read SKILL.md in full, then run the coding-review-agent-loop orchestration.
How to install Coding Review Agent Loop
Installs to ~/.claude/commands/wwind123-coding-review-agent-loop-coding-review-agent-loop.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/wwind123/coding-review-agent-loop/HEAD/.claude/commands/coding-review-agent-loop.md -o ~/.claude/commands/wwind123-coding-review-agent-loop-coding-review-agent-loop.md Restart Claude Code, or start a new session, for it to be picked up.
What Coding Review Agent Loop does
Read `SKILL.md` in full, then run the coding-review-agent-loop orchestration.
Arguments provided by the user: $ARGUMENTS
Parse the arguments to extract:
- repo (
OWNER/REPO) — required - flow —
issue(maps to--flow plan) orpr(maps to--flow pr) - reviewers —
--reviewers codex,gemini, or both (default: gemini) - plan-first — present if the user passes
--plan-first(only relevant for issue flow) - coder —
--coder claude(default),--coder codex,
Alternatives in Development
- /discover — Run a full discovery loop without manually stitching together skills 2.3k ★
- Evo — turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then run 1.4k ★
- Purpose — Orient yourself in pi-vs-cc — a collection of Pi coding agent extensions and agent specs that progressively de 527 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Feature Forge
A full feature lifecycle for coding agents: crucible, brief, wireframe, architecture, plan, TDD build loop, ad
Tether
a local CLI orchestration layer that makes autonomous coding agents more reliable. It wraps any coding agent (
Daily Loop
Daily run. Read CLAUDE.md, charter.md, state.md, then yesterday's entries in ledger.md and decisions.md.
Monitor Log Agent
An example of a read-only Claude Code agent: a Python host prepares context, then Claude Agent SDK runs the ag
Batchc
Smartbatch execution protocol. Read the full prompt before touching anything, then:
Gemini Headless Upgrade
Gemini-directed autonomous headless-upgrade loop, merged with the full 13-section orchestrator framework. gemi
Related Agents
Loop Reviewer Spec
full-loop S6 검수 1 — AC 체크리스트 항목별 명세 대조(READ 기반). 산출 컨텍스트를 공유받지 않고 AC와 산출물 경로만으로 독립 채점한다.
Vision
GSD-2 is the orchestration layer between you and AI coding agents. It handles planning, execution, verificatio
Docstring Writer
Adds/refreshes docstrings and doc-comments for changed source in the orchestration deliver stage, then leaves