multi-agent
v0.4.6Workflow and model-routing guidance for multi-agent work: assess (workflow, subagent or single context), route (the role map a workflow script reads from args, keeping fan-out stages off a frontier model), audit-defaults (rechecks bundled defaults against upstream, or sweeps the repo's model and workflow guidance, via a read-only drift-audit workflow), check (whether node resolves and the fetch gate is registered), and setup (writes a user, team or local layer after a preview and a yes).
By Melodic SoftwareLicense: MIT21 GitHub starsUpdated 2 days ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 5 skill or MCP entries
- Source updated
- Oct 4, 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 multi-agent for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install multi-agent@agent-plugin-marketplacePaste 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/melodic-software/claude-code-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/multi-agent/.
Plugin files
├── .claude-plugin/plugin.json├── skills/assess/SKILL.md├── skills/audit-defaults/SKILL.md├── skills/check/SKILL.md├── skills/route/SKILL.md└── skills/setup/SKILL.md
Included Skills5
Decide whether a task should run as a workflow, as delegated subagents, or in this single context, and say why in one line; checks first whether workflows are available in this session and downgrades `workflow` to `subagent` when they are not. Writes nothing. Use when: 'should this be a workflow', 'workflow or subagents', 'is this worth a workflow', 'how should I orchestrate this', 'fan this out or do it inline', 'is the Workflow tool available', or before a skill launches a workflow.
Recheck every bundled multi-agent role default (model, effort, the fan-out guard) against the upstream pointer recorded beside it, and report which defaults have drifted or whose recheck trigger has fired, each with fetched evidence and a proposed diff to reference/defaults.yaml; `repo` mode sweeps the repository's own model, effort, subagent and workflow guidance for stale or copied upstream claims. Proposes only; never edits a file. Use when: 'are the routing defaults current', 'audit the role map', 'recheck model defaults', 'did the workflow guidance change', 'new model released, check the defaults', 'is our model guidance stale', or when an as-of date in defaults.yaml looks old.
Read-only check that node resolves for the multi-agent drift-checker fetch gate hook and that the hook is registered. Use when a hook notice says node is missing, or before assuming the fetch gate ran. Does not install.
Resolve which model and effort each agent role gets in a multi-agent run (orchestrator, worker, verifier, retrieval) through the bundled defaults and the user, team and overlay config layers, and print it as fenced JSON with a single-agent and a fan-out variant per role and the layer that supplied each value. A fan-out stage never runs on a frontier model unless the config opts in. Use when: 'which model for the subagents', 'route the roles', 'what effort should the workers use', 'roles for the workflow args', 'model routing', 'is fan-out on Fable', or before a skill launches a workflow that takes args.roles.
Configure the multi-agent role map for a person or a repository: check prints the resolved map (model and effort per role, single and fan-out variants, the layer behind each value) and whether the personal overlay is gitignored; apply writes the keys you confirm into the user-global, team or local multi-agent.yaml layer, showing the map before and after. Use when: 'set up multi-agent', 'configure model routing', 'change the worker effort for this repo', 'turn off the fan-out guard', 'which layer sets the verifier model', 'multi-agent setup'. Re-runnable.
Plugin manifests1
{
"name": "multi-agent",
"version": "0.4.6",
"description": "Workflow and model-routing guidance for multi-agent work: assess (workflow, subagent or single context), route (the role map a workflow script reads from args, keeping fan-out stages off a frontier model), audit-defaults (rechecks bundled defaults against upstream, or sweeps the repo's model and workflow guidance, via a read-only drift-audit workflow), check (whether node resolves and the fetch gate is registered), and setup (writes a user, team or local layer after a preview and a yes).",
"author": {
"name": "Melodic Software",
"email": "[email protected]"
},
"license": "MIT",
"keywords": [
"workflow",
"orchestration",
"subagents",
"model-routing",
"effort",
"fan-out",
"skill"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[multi-agent on Agent Plugins Marketplace](https://pluginsmp.com/plugins/multi-agent)