AugmentClaude
FeaturedAgent

πŸ”Code Reviewer

Reviews your code changes for bugs, security holes, and weak spots before merge.

What it does

What it does: Runs a structured, security-first code review on your pending changes and returns prioritized findings with fixes.

  • Establishes diff scope from git diff, scales its reading depth to change size, and runs pre-checks for CVEs (npm audit/pip-audit/cargo audit) and hardcoded secrets before reading code
  • Works through a checklist covering security (injection, auth bypass, leaked PII), error handling, test quality, dependencies, and performance (N+1 queries, unbounded loads)
  • Applies language-specific rules for TypeScript, Python, Rust, Go, and SQL β€” flagging any, mutable default args, stray .unwrap(), discarded errors, and WHERE-less UPDATE/DELETE
  • Reports every finding as CRITICAL/HIGH/MEDIUM/LOW with file:line, the risk, and a concrete fix, then closes with a merge recommendation of BLOCK, APPROVE WITH SUGGESTIONS, or APPROVE
  • Frames feedback constructively β€” explains the risk over the rule, offers alternatives, and acknowledges code that's done well

Installation

  1. Make sure Claude is on your device and in your terminal.

    Agents load from ~/.claude/agents/ when Claude Code starts. If you don't have Claude Code yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into your terminal.

    Downloads the agent into ~/.claude/agents/code-reviewer-wshobson.md. Safe to re-run; it just overwrites.

  3. Restart Claude Code.

    Quit and reopen Claude Code. New agents are picked up on startup.

  4. Use it.

    Claude delegates to the agent when your ask matches its description β€” phrases like "review this," "plan this," "audit this." You can also invoke directly: "Use the code-reviewer-wshobson agent to…"

Prefer to read the source first? Open on GitHub.