Skill Claude CodeCodex
A command that checks CodeBrain's health and reports only failed checks.
Skill Claude CodeCodex
A command that checks CodeBrain's health and reports only failed checks.
Skill Claude CodeCodex
A one-line health-reporting command for Code Brain, a coding-agent support system. It checks diagnostics, workers, queues, and the file index.
Skill Claude CodeCodex
A command for testing whether CodeBrain's code-search context is useful and consistent. It compares search versions, ranking, latency, size limits, and other reported checks.
Skill Claude CodeCodex
A command that applies the latest version of a migrated source repository to CodeBrain, a coding-agent setup.
Skill Claude CodeCodex
A usage-reporting command for Code Brain, a coding-agent support system. It summarizes Codex activity, token use, hooks, and MCP tool calls.
Command Claude Code
A command that runs the code-brain doctor check and prints only failed checks, or one line saying all checks passed. Its output rules are in Korean.
Command Claude Code
A command that runs a shell command in Code Brain’s sandbox and summarizes the result. A sandbox is an isolated environment for running commands with controlled access.
Command Claude Code
A command that summarizes CodeBrain's operational status, including checks, background workers, queued jobs, and indexed files.
Command Claude Code
A command that compares two versions of code-brain context search and reports ranking, repeatability, storage, latency, and context-size results.
Command Claude Code
A search command for Code Brain that finds matching indexed files using BM25, a relevance-based text-search method.
Command Claude Code
A command that upgrades the Codebrain repository to its latest public version. It updates files over the network and requires a new Claude, Codex, or Antigravity session before the new rules apply.
Command Claude Code
A command that reports Code Brain activity, including Claude and Codex token use, hook and MCP activity, and blocked tool calls. Hooks are automatic project actions, while MCP is a way for an agent to call connected tools.
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.
Instructions file
Instructions for ezBuilder/code-brain, covering code brain agent contract, response, branches, loop and planning.
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
Run the Claude/Codex kit doctor from the installed kit directory.
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
Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.sh. From ezBuilder/code-brain.
Hook Claude Code
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
Runs after a tool call finishes for Bash, Edit, MultiEdit and Write tool calls, executing post-tool-use.sh. From ezBuilder/code-brain.