影武者 / kagemusha: a Markdown governance kit for Claude Code and AI agents—approval queues, correction promotion, and judgment distillation.
Skill Claude CodeCodex
A procedure for consulting a frontier-class external reasoning model (extended-thinking tier) on a decision that matters — and for accepting its answer afterwards. Generates the consultation prompt, then audits the reply. Vendor-neutral: any top-tier model will do. Not for routine work sent to a cheap model — that is…
Skill Claude CodeCodex needs its repo
A two-machine live meeting copilot. A Windows laptop streams two audio channels (your mic, and a loopback of the other side's voice) to a parent machine, which transcribes them, drives a teleprompter you read from, watches every incoming utterance against a ledger of pre-agreed facts, and answers off-script questions.…
Skill Codex
Use when the user asks Codex Desktop to consult a user-selected ChatGPT Web model through the standard in-app Browser and capture its final answer. Not for API calls, external browser automation, or prompt drafting without sending.
Skill Codex
Plan and deliver high-rework software changes in Codex Desktop by consulting a user-selected ChatGPT Web Pro model for pivotal design decisions, then implementing against an audited design contract. Use when the user asks for Pro-led strategy or design followed by Codex implementation; do not use for routine debugging…
Skill Claude CodeCodex
A one-machine live meeting board. A small browser extension reads Google Meet's own live captions together with the speaker names, hands them to a tiny helper that listens on 127.0.0.1 only, and the helper periodically asks the local Claude Code (claude -p) to keep a structured, speaker-attributed "story so far".…
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: