graphhelm-chat
v0.1.0Operate GraphHelm executions from chat: the graphhelm mcp stdio server plus three skills (operate-execution, observe-agents, leave-records). Thin and deletable: everything here is `graphhelm mcp` plus documented CLI calls.
By GraphHelm0 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Sep 26, 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 graphhelm-chat for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install graphhelm-chat@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/stabem/GraphHelmClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is examples/chat-surface/claude-code-plugin/.
Plugin files
├── .claude-plugin/plugin.json├── skills/leave-records/SKILL.md├── skills/observe-agents/SKILL.md├── skills/operate-execution/SKILL.md└── .mcp.json
Included Skills3
Leave records in an execution's log while working, for a person watching the Studio who is not at this terminal - at a decision you cannot make alone, a finding that changes the plan, a blocker, or before something hard to undo. Use also when checking whether that person has answered.
Multi-agent visibility, read-only - who is acting on this execution right now and what did they do, derived entirely from the events tail's attribution. Use when the user asks what other agents or sessions are doing, or to review an interleaved actor timeline.
The operator loop for one GraphHelm execution - start it, watch the tail, surface triage items, act on them, report the outcome with evidence references. Use when the user wants to run, supervise, unblock, pause, resume, or cancel an execution from chat.
MCP servers1
- command
- graphhelm
- args
- mcp --url http://127.0.0.1:8080 --token-file ${GRAPHHELM_TOKEN_FILE} --actor agent-chat
Plugin manifests1
{
"name": "graphhelm-chat",
"description": "Operate GraphHelm executions from chat: the graphhelm mcp stdio server plus three skills (operate-execution, observe-agents, leave-records). Thin and deletable: everything here is `graphhelm mcp` plus documented CLI calls.",
"version": "0.1.0",
"author": {
"name": "GraphHelm"
}
}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.
[graphhelm-chat on Agent Plugins Marketplace](https://pluginsmp.com/plugins/graphhelm-chat)