alvis-HaoH

9 mods across 1 repository, 10 stars between them.

gkd

01

alvis-HaoH/gkd

Plugin Claude Code

A Claude Code plugin that delegates tasks to other AI models, including GLM, Kimi, DeepSeek, or a local Codex command-line tool.

10 1mo ago A tokens not measured original MIT

gkd

02

alvis-HaoH/gkd

Plugin Claude Code

A task-delegation plugin that sends work to other AI models or a local Codex command-line agent, one task at a time or in batches.

10 1mo ago A tokens not measured original MIT

ask

03

alvis-HaoH/gkd

Command

A read-only command for asking another AI model to answer, analyze, review, or advise on a task. It can include relevant conversation context and lets the user choose thinking effort or a model.

10 1mo ago A 43 tokens original MIT

brainstorm

04

alvis-HaoH/gkd

Command

A command that asks several AI models for separate answers to the same question before the main agent combines them.

10 1mo ago A 51 tokens original MIT

do

05

alvis-HaoH/gkd

Command

A command for delegating coding tasks to another AI model. In write mode, the delegated process can read and change files and run commands, with options for model choice, context, effort, and continuing earlier sessions.

10 1mo ago A 42 tokens original MIT

resume

06

alvis-HaoH/gkd

Command

A command for continuing a previously delegated task, either from the current folder or from a named past session. A session is the saved context of an earlier delegated task.

10 1mo ago A 53 tokens original MIT

review

07

alvis-HaoH/gkd

Command

A command that delegates a read-only review of local Git changes to another model. Git is the version-control system used to track code changes.

10 1mo ago A 44 tokens original MIT

stats

08

alvis-HaoH/gkd

Command

A command that reports token usage and estimated savings for delegated model work, normally covering the last seven days.

10 1mo ago A 27 tokens original MIT

workflow

09

alvis-HaoH/gkd

Command

A command that turns a list of similar tasks into a workflow, giving each item its own separate model process to handle in parallel.

10 1mo ago A 50 tokens original MIT