motoedie/motoedie-utils

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Add, review, or rewrite code comments so they explain intent, invariants, branch rationale, and multi-step flows without narrating obvious syntax. Use when documenting newly added or recently changed code, converting line-by-line comments into concise block comments, checking whether comment density is too sparse or too heavy, or making non-obvious branches, scripts, and side effects easier for reviewers to scan.

Resolve git conflicts by understanding intent on every side, not by picking a winner. Use when an integration step (merge, rebase, cherry-pick, revert, or — only on explicit request — stash apply) left files with <<<<<<< markers. Scope is conflict resolution only — does not commit, continue, drop, or otherwise advance the integration.

Structure an implementation plan for a coding AI agent to execute autonomously. Use when preparing a multi-phase coding task that another agent (or future session) will carry out without human intervention. Produces a self-contained plan document with all context an agent needs.

Create, audit, optimize, or test Agent Skills for coding agents. Use when designing a new skill or improving an existing skill's routing, instructions, token economy, resources, portability, safety, or evaluations. Existing-skill work is report-first and requires approval before edits. Do not use for ordinary prompt editing or unrelated documentation.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.