🧠 Give Claude Code the operating context it's missing: persistent rules, enforced hooks, on-demand skills and deep knowledge of your codebase.
brain-bootstrap/claude-code-brain-bootstrap
Agent Claude Code
Adversarial plan review before implementation. Attacks plans across 5 dimensions (Assumptions, Missing Cases, Security, Architecture Fit, Complexity Creep), then self-refutes to eliminate false positives.
brain-bootstrap/claude-code-brain-bootstrap
Agent Claude Code
Deep codebase exploration and analysis. Delegates read-only research to a separate context window, preserving the main conversation for implementation. Use for tracing code paths, finding patterns, gathering context.
brain-bootstrap/claude-code-brain-bootstrap
Agent Claude Code
Expert code reviewer for MR analysis. Runs the 10-point review protocol in an isolated context, checking cross-layer consistency, transaction safety, enum completeness, and test coverage. Returns a structured review report.
brain-bootstrap/claude-code-brain-bootstrap
Agent Claude Code
Security-focused analysis: scan for secrets, vulnerabilities, auth gaps, dependency risks, and compliance issues. Use before deployment or when touching auth/crypto/data-handling code.
brain-bootstrap/claude-code-brain-bootstrap
Agent Claude Code
Analyze conversation patterns to detect recurring frustrations, corrections, and problematic tool usage. Feeds findings to CLAUDEERRORS.md or lessons.md. Use after long sessions or when you want to extract learnings.