MCP App StoreMCP App Store
from cross-review-skill13
Facilitates a second-opinion review by invoking the opposite AI reviewer (Codex vs Claude Code) to assess design and code changes.
This skill enables an agent to seek a 'second opinion' by calling the opposite CLI reviewer. If the host is Codex, it invokes Claude Code; if the host is Claude Code, it invokes Codex. This reduces confirmation bias and identifies risks the primary agent might miss.
Activate this skill when a user asks for a cross-review, second-opinion, or a 'Codex-vs-Claude' assessment of a proposal, design change, or complex code regression analysis.
scripts/run-cross-review.sh for managing the external call and capturing the assessment.Requires both codex and claude CLI tools to be installed and authenticated on the host machine.
This skill has not been reviewed by our automated audit pipeline yet.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo
AI Pair Collaboration
Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate
Box0 (b0)
Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.
Crucible: Build
Orchestrates an end-to-end development pipeline: interactive design, planning, autonomous execution, and quality gates with TDD and iterative reviews.
Code Reviewer
Perform structured, prioritized code reviews that find correctness, security, performance, reliability, and testing issues and provide concrete fix suggestions.