review-correctness

Reviews changed code for logic and behavior defects that deterministic tooling cannot catch, including behavioral regressions on the surface tests do not cover. Spawned by the pr-ci-review skill.

4rigs use it

0%of all rigs

3.5kavg rig context tax

Get it

$ npx degit trailofbits/coop/.claude/agents .claude/agents

From the most-starred rig that ships it: trailofbits/coop. Same-named subagents in different rigs may differ — review before use.

Often used together with

review-conventions · 4 review-docs · 4 review-security · 4 prototype · 2 grill-me · 2 implement · 2 research · 2 handoff · 2 tdd · 2 caveman · 2

Rigs using review-correctness (4)

trailofbits/coop

Isolated VM environment for running Claude Code and Codex

★ 741 project Claude CodeCodex 6 skills 8 agents 3 hooks 7d ago

Orchestrator 2.7k tok ·

JDevlieghere/dotfiles

⚙ Dotfiles for Linux & macOS

★ 303 setup Claude Code 6 skills 10 agents 4d ago

Orchestrator 1.5k tok ·

AlexisBalayre/claude-code-config

Opinionated Claude Code config: path-scoped rules, 34 skills, 12 subagents, deterministic hooks, and a multi-agent PR review. Stack-agnostic; run /adapt-to-project to fit any repo.

★ 2 setup Claude CodeCodex 1 mcp 34 skills 12 agents 7 hooks 4d ago

Fort Knox 6.4k tok ·

AlexisBalayre/agentspine

One shared agent setup for Claude Code, Codex, opencode, Mistral Vibe and Cursor: AGENTS.md, skills and blocking hooks stored once in .agents/ and wired into every tool.

★ 0 project Claude CodeCodex 29 skills 7 agents 2 hooks 4d ago

Orchestrator 3.3k tok ·