Review Context — Data & AI agent for Claude Code
Pre-review architectural context gatherer.
How to install Review Context
Installs to ~/.claude/agents/arcasilesgroup-claudeline-review-context.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/arcasilesgroup/claudeline/HEAD/.claude/agents/review-context.md -o ~/.claude/agents/arcasilesgroup-claudeline-review-context.md Restart Claude Code, or start a new session, for it to be picked up.
What Review Context does
name: review-context description: Pre-review architectural context gatherer. Explores the codebase beyond the diff to produce a structured summary that all review specialists consume. Dispatched by ai-review before any specialist runs. model: opus color: cyan tools: [Read, Glob, Grep, Bash] mirror_family: specialist-agents generated_by: ai-eng sync canonical_source: .claude/agents/review-context.md edit_policy: generated-do-not-edit
Runs **before** the review specialists to gather the
Alternatives in Data & AI
- Visual Explainer — Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews 6.8k ★
- Technical Analyst — Specialized agent for technical analysis of B3 stocks 124 ★
- Code Preview.Nvim — A Neovim plugin that shows a live diff preview of AI coding agent's file edits before you accept or reject the 92 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Review Validator
Adversarial validation agent. Receives ONLY the YAML finding block (no reasoning chain) and reads the code fre
SEO Strategist
Top 1% SEO strategist agent — analyzes GSC, Bing, and GA4 data to produce data-driven ranking strategies, keyw
Foley
Backlog triage analyst — stage 1 of the backlog pipeline. Invoke with pre-fetched task data to assess dispatch
Repo Mapper
Maps a codebase by analyzing detection data and config files to produce a per-module registry with tailored an
AI Context
Compresses discovery output into the single structured task-context document every later agent reads instead o
Falsification Leg
Standing pre-merge falsification leg (mmnto-ai/totem-strategy:doctrine/model-tiering.md § Review legs). Dispat
Related Skills
Summary
Produce a summary so another session can continue with zero context beyond CLAUDE.md, the codebase, and the su
Codex Review
Run a Codex Council-of-models review on the current diff and produce a triaged summary
Learning Summary
You are analyzing a completed sub-agent coding task to produce a structured learning summary.