mattdurham

Generate a self-contained, navigable explainer bundle for a feature of the current codebase — a sidebar of sub-concepts, detail pages, and linked animated diagrams grounded in the real code

Analyze a codebase and interactively generate an OKF (.knowledge/) bundle — asks clarifying questions, discovers packages and decisions, then writes a complete navigable knowledge catalog.

Analyzes code for unnecessary complexity, unjustified abstractions, and structural cleanup opportunities using first-principles engineering methodology

Finds bugs in existing code — nil dereferences, race conditions, resource leaks, logic errors, error handling gaps. Creates cleanup tasks for each finding.

Verifies that SPECS.md, NOTES.md, TESTS.md, BENCHMARKS.md, and documentation cross-reference cleanly against each other and against the actual code

Self-directed analyst that claims analysis tasks from a shared task list and writes findings (read-only)

Researches the codebase for a brainstorm task, evaluates multiple approaches, and writes findings to a brainstorm file

Self-directed challenger that claims completed analysis tasks and stress-tests them (read-only)

Memory-driven team workflow with AST-aware code editing via grv — agents read and write Go code through the grv tool instead of raw file I/O. INIT → WORKTREE → BRAINSTORM → PLAN → EXECUTE → REVIEW → COMPLETE

Memory-driven team workflow — agents bootstrap their own guidance from lth before working. INIT → WORKTREE → BRAINSTORM → PLAN → EXECUTE → REVIEW → COMPLETE

Generate a structured task brief from lth memory before starting work

Retroactively store session learnings to lth memory without manual store calls

Session warmup — surface recent project context from lth memory

Bootstrap agent memory from lth — reconstruct context from stored memories before working, store findings after