Agent Plugins Marketplace
All plugins

graph-sorcerer

v0.1.0

Designs agent graphs — and refuses to build one when the work isn't actually wide. Runs a fake-edge test before fanning out, enforces fresh-context verifiers and a hard agent cap, and never launches a fleet without your go-ahead.

Claude Code1 Skill

By Dibakar UpadhyayaLicense: MIT0 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Aug 27, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install plugin

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install graph-sorcerer@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/Dibakar01/graph-sorcerer

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

graph-sorcerer/
├── .claude-plugin/plugin.json
└── skills/graph-sorcerer/SKILL.md

Included Skills1

graph-sorcererskills/graph-sorcerer/SKILL.md

Use when work may be wide enough to run as a fleet of parallel agents rather than one — any "do X for each of these N things" job across many files, sources or angles. Also use when asked to design a graph, a dynamic workflow or an ultracode run; to parallelize, fan out or speed up a slow chain of agent steps; or to judge whether a job should be a graph at all. Reach for it before spawning parallel agents by hand — establishing that a job is NOT wide enough is one of its main jobs.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "graph-sorcerer",
  "version": "0.1.0",
  "description": "Designs agent graphs — and refuses to build one when the work isn't actually wide. Runs a fake-edge test before fanning out, enforces fresh-context verifiers and a hard agent cap, and never launches a fleet without your go-ahead.",
  "author": {
    "name": "Dibakar Upadhyaya",
    "url": "https://github.com/Dibakar01"
  },
  "homepage": "https://github.com/Dibakar01/graph-sorcerer",
  "repository": "https://github.com/Dibakar01/graph-sorcerer",
  "license": "MIT",
  "keywords": [
    "agents",
    "parallel",
    "workflow",
    "orchestration",
    "subagents",
    "fan-out",
    "graph",
    "cost-control"
  ]
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[graph-sorcerer on Agent Plugins Marketplace](https://pluginsmp.com/plugins/graph-sorcerer)