matheusht

matheusht/redthread

Skill Claude CodeCodex

Instructions for triggering external Context7 connections.

matheusht/redthread

Skill Claude CodeCodex

Algorithms for LLM-as-a-Judge telemetry and rule synthesis.

matheusht/redthread

Skill Claude CodeCodex

Structural audit skill invoked against plans prior to execution to resolve missing edge cases.

matheusht/redthread

Skill Claude CodeCodex

Isolated task-building phase after approval. Strongly encourages Subagents.

matheusht/redthread

Skill Claude CodeCodex

Lightweight research-plan-implement workflow for small tweaks, isolated bugfixes, copy edits, and low-blast-radius polish in this repo. Use when the change can be understood from 1-3 files and stays inside one subsystem without changing shared data flow.

matheusht/redthread

Skill Claude CodeCodex

Defines the formal step-by-step logic map before taking action.

matheusht/redthread

Skill Claude CodeCodex

Implements tree-based attack branching and prompt refinement optimization.

matheusht/redthread

Skill Claude CodeCodex

Sweeping file aggregation and pattern recognition across the repository. Does not modify files.

matheusht/redthread

Skill Claude CodeCodex

Full research-plan-implement workflow for new features, architectural updates, multi-file changes, or any task with non-trivial blast radius in RedThread.

matheusht/redthread

Instructions file CodexOpenCode

AGENTS.md instructions for matheusht/redthread, covering redthread agent architecture, 1. core operating guidelines, 2. the orchestration workflow (principal vs subagents), the principal agent must and subagent usage.

matheusht/redthread

Skill Claude CodeCodex

Ultra-compressed communication mode. Cuts token usage 75% 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…