Review Bug — Development agent for Claude Code
Review: Bug/Logic Error Detection (coverage-first) — report all findings with confidence and severity tags; downstream verification sub-agents filter false positives.
How to install Review Bug
Installs to ~/.claude/agents/saitoco-wholework-review-bug.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/saitoco/wholework/HEAD/agents/review-bug.md -o ~/.claude/agents/saitoco-wholework-review-bug.md Restart Claude Code, or start a new session, for it to be picked up.
What Review Bug does
name: review-bug description: Review: Bug/Logic Error Detection (coverage-first) — report all findings with confidence and severity tags; downstream verification sub-agents filter false positives tools: Read, Glob, Grep, Bash(git log:*, git diff:*, git show:*) model: opus effort: high
Review: Bug/Logic Error Detection
**Note (cyber classifier):** This agent's default model (`model: opus` above) currently resolves to Opus 5, which carries its own cyber classifier (~85% lower trigger
Alternatives in Development
- TAGS — Tag Vocabulary 2.3k ★
- Seam Analyzer — Hunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held to 2.2k ★
- [Breakthrough Title] — Date: YYYY-MM-DD Tags: #performance #architecture #algorithm (relevant tags) 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Dead Code Hunter
Verifies dead code findings from knip/grep. Reads actual source files to filter false positives. Cites file:li
Verify Finding
Cheap pre-filter for §6 review findings — scores a whole batch of findings 0-100 each for whether they are rea
Scout Reviewer
Use this agent when you need a thorough PR review performed on your behalf. Scout uses the /code-auditor's par
Cr Code Reviewer
Generalist compliance and bug-detection pass over the PR diff, filtered hard for confidence. Spawn on feature-
Markdown Investigator
Autonomous analyzer that determines if markdown errors are fixable or false positives
Light Review Step2
Stage 2 of the Delphi review pipeline — counter-analyze the findings of a prior light-review-step1 run. Drops
Related Skills
Slice Review
Run a multi-agent code review over a local diff (no PR or remote required) and report findings by severity wit
Klarion
AI-powered secret scanner for code and git history. Finds leaked API keys, tokens and credentials with near-ze
Paper Reader
A Claude Code skill for critical paper reading: 4 modes (deep-read, quick-scan, recommend, lit-review) with ev