Self-deploying cross-tool AI harness — one canonical source deployed to Claude Code, Codex, Cursor, Devin, Antigravity & 9 more. Loop engineering, three-layer memory, worker personas, hooks, MCP, vault.
masteryee-labs/Tool.Agent-Harness-Deploy
Skill Claude CodeCodex
A workflow for researching a person's ideas and turning the resulting thinking patterns into a usable agent skill. For unclear requests, it first identifies the kind of adviser the user needs; for a named person, it distills that person's mental models, decision rules, writing style, limits, and things to avoid.
masteryee-labs/Tool.Agent-Harness-Deploy
Skill Claude CodeCodex
A thinking and communication framework based on Richard Feynman’s publicly documented methods and ideas. It focuses on checking whether an explanation reflects real understanding rather than memorized terms.
masteryee-labs/Tool.Agent-Harness-Deploy
Skill Claude CodeCodex
A Chinese-language thinking framework based on Charlie Munger’s public ideas, including mental models, decision rules, and checks for thinking errors. It is an interpretation of public material, not advice from Munger himself.
masteryee-labs/Tool.Agent-Harness-Deploy
Skill Claude CodeCodex
A set of thinking and writing guidelines based on Nassim Nicholas Taleb's published ideas and public conversations. It examines decisions through concepts such as rare extreme risks, unequal outcomes, personal exposure to consequences, and resilience to shocks.
masteryee-labs/Tool.Agent-Harness-Deploy
Skill Claude CodeCodex
Local hybrid retrieval (BM25 + ChromaDB vector + BGE-Reranker) over /.deep-memory hot and cold stores. Use when high-accuracy code/solution retrieval is needed and hallucination must be minimized. Typically invoked by deep-memory.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: