Skill Claude CodeCodex
A lightweight framework for making technical decisions by checking system impact, boundaries, maintenance, constraints, and outside dependencies.
not rated 5 1mo ago A 0 tokens
original MIT
5Stars on the repository
10Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
DevTrace
02Skill Claude CodeCodex
An engineering decision framework for software architecture, technology choices, code reviews, refactoring, technical debt, and project risks. It examines dependency structure, abstraction layers, uncertainty, limits, and interactions before suggesting a change.
not rated 5 1mo ago A 0 tokens
original MIT
FOUDF
03Skill Claude CodeCodex
A general framework for thinking through complex decisions with many connected factors and uncertain outcomes. It examines relationships, layers of explanation, probabilities, limits, and how people or systems affect one another.
not rated 5 1mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
Repository-level routing index for the qinghuan-lp-agent-skills collection. Use when deciding which bundled skill to activate across this repo. Route complex general decisions to FOUDF, engineering and architecture analysis to DevTrace, reverse engineering, malware, obfuscation, anti-debugging, protocol recovery, or…
not rated 5 1mo ago A 124 tokens
original MIT
Skill Claude CodeCodex
A skill for splitting a function out of the main coding agent into a separate agent with its own sessions, workspace, memory, identity, and keep-alive process.
not rated 5 1mo ago C 97 tokens
original MIT
Skill Codex
Establish and enforce a truthful local-only authorization scope before reverse engineering, debugging, or runtime instrumentation with IDA MCP, Frida, Ghidra, LLDB, or similar tools. Use when Codex is asked to analyze an app or binary loaded on the user's machine, attach to an app on the user's own jailbroken phone…
not rated 5 1mo ago A 114 tokens
original MIT
Skill Claude CodeCodex
A design for an LLM or multi-agent system that keeps several possible explanations alive, weighs evidence, filters constraints, and revises its conclusions. An LLM is a language model; a multi-agent system uses several such agents or roles.
not rated 5 1mo ago A 0 tokens
original MIT
todoist
08Skill Claude CodeCodex
Todoist task management for OpenClaw. Unified todo API with multi-agent identity, scheduled checks and reminders.
not rated 5 1mo ago A 25 tokens
original MIT
Skill Claude CodeCodex
Reverse engineering meta-cognitive activation engine. Manages attention allocation, noise suppression, task-mode routing, object typing, hypothesis branching, mental model switching, and analysis boundary judgment at a meta level. Use when performing reverse engineering, binary analysis, malware analysis, obfuscation…
not rated 5 1mo ago A 136 tokens
original MIT
Skill Claude CodeCodex
Set up and use a practical Ghostty + tmux workflow with clear naming, fresh home-directory tabs, simple tmux entry, session switching, and save/restore shortcuts. Use when the user wants to configure Ghostty/tmux, understand the difference between tabs, sessions, windows, and panes, create reusable terminal…
not rated 5 1mo ago A 81 tokens
original MIT
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: