gkd

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.

In plain words
What is it for?
Use it for delegation, batch workflows, brainstorming, and cross-review of code, writing, visual work, or reasoning.
Why use it?
It lets the main agent hand off suitable work, reduce its own token use, or get independent viewpoints.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add alvis-HaoH/gkd
agentmods
npx agentmods add plugins/alvis-haoh/gkd/gkd
Clone the repo
git clone --depth 1 https://github.com/alvis-HaoH/gkd

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 7 commands cost 310 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

gkd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "gkd",
  "description": "搞快点(GKD,也是 GLM/Kimi/Deepseek 首字母)——任务委派 plugin。借 Claude Code 的工具循环 harness,把任务派给以其他模型为大脑的claude code;也可用 --codex 委派给本机 codex CLI(GPT 在自家 harness 里干活)。两个并重的目的:省主 Claude 的 token(可降级的活交给便宜模型),以及借不同模型/harness 的视角(代码/长文/视觉/推理 各有所长,brainstorm/cross-review 跳出单一模型定式)。覆盖单任务委派、batch workflow、多模型 brainstorming。",
  "author": {
    "name": "alvis-HaoH",
    "url": "https://github.com/alvis-HaoH"
  },
  "homepage": "https://github.com/alvis-HaoH/gkd",
  "repository": "https://github.com/alvis-HaoH/gkd",
  "license": "MIT",
  "keywords": [
    "delegation",
    "cost-saving",
    "token-saving",
    "subagent",
    "workflow",
    "brainstorm",
    "codex",
    "gpt"
  ]
}
Contents

What it installs

The manifest is a name and a version. 7 commands travel with it, and installing the plugin installs all of them — 310 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 22 lines scan A dd10ed9e2549

Subscribe to this mod's changes

gkd is a plugin published in the GitHub repository alvis-HaoH/gkd (10 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.