code-brain
01MCP server Claude CodeCodexCursor +2
MCP server "code-brain" as configured in ezBuilder/code-brain. Launched with .ai/bin/ai-mcp. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "code-brain" as configured in ezBuilder/code-brain. Launched with .ai/bin/ai-mcp. Needs 2 environment variables to run.
Agent Claude Code
A separate agent for reviewing complex codebase decisions, large refactors, and difficult cause analysis. A refactor changes internal code structure while aiming to preserve behaviour.
Agent Claude Code
A separate agent for researching an existing codebase, including its patterns, affected areas, and similar implementations. It reports evidence from specific files, functions, and lines without changing files.
Agent Claude Code
A separate agent that reviews security-sensitive code changes without editing files or reading sensitive configuration. It focuses on authentication, permissions, payments, deletion, and handling of outside input.
Agent Claude Code
A test-reviewing subagent that checks whether code changes have enough tests and identifies how they should be verified.
Command Claude Code
Research Claude Code and Codex CLI changes before modifying this kit.
Command Claude Code
Run one autonomous kit upgrade iteration.
Hook Claude Code
One of 5 in settings.json
Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.sh. From ezBuilder/code-brain.
Hook Claude Code
One of 5 in settings.json
Runs before the agent uses a tool for Bash, Read, Edit and Write tool calls, executing block-dangerous.sh, block-secret-commit.sh and protect-secrets.sh (3 commands). From ezBuilder/code-brain.
Hook Claude Code
One of 5 in settings.json
Runs after a tool call finishes for Bash, Edit, MultiEdit and Write tool calls, executing post-tool-use.sh. From ezBuilder/code-brain.
Hook Claude Code
One of 5 in settings.json
Runs when a session starts on startup, resume, clear and compact, executing session-context.sh. From ezBuilder/code-brain.
Skill Claude Code
Build, install, run, and verify a reusable image-to-game-ready-3D pipeline for Unity with controlled ImageGen references, approved AI mesh providers, Blender MCP/CLI, modular era catalogs, Blender retopology/LOD/pivot processing, and Unity import/render proof. Use for 2D-to-3D assets, vehicles, aircraft, ships…
Skill Claude Code
A checklist and audit guide for in-app purchases, subscriptions, and quota billing. It covers store verification, user entitlements, webhooks, reconciliation, and an append-only ledger, which is a record where entries are added rather than rewritten.
Skill Claude Code
A checklist for reviewing code changes before they are merged into a shared codebase. It checks whether the changes match the request and follow project rules.
Skill Claude Code
A bug-diagnosis workflow that uses records of earlier failures, decisions, and lessons. It checks whether past findings still apply to the current version and environment before investigating the code.
Skill Claude Code
A workflow for reproducing a software bug, identifying its cause, and applying the smallest fix. It includes focused verification and optional failure-first tests.
Skill Claude Code
A process for implementing a requested software feature with the smallest necessary change.
Skill Claude Code
A read-only scanner for intentional simplification markers in a code repository. These markers record code that has a known limit and should be revisited when a stated condition occurs.
Skill Claude Code
A review focused only on code that may be more complicated than needed. It identifies candidates for deletion, standard-library or built-in replacements, and shorter equivalent code.
Skill Claude Code
A small-step refactoring workflow that keeps existing behavior unchanged. Refactoring means improving code structure without intentionally changing what the software does.
Skill Claude Code
A test-first implementation workflow that recalls past decisions, conventions, and lessons before coding. TDD, or test-driven development, means writing a failing test first, then implementing the code and finally cleaning it up.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: