/reload-mcp
Gracefully cycle dashboard and audit MCP processes after deliberation is updated.
$ npx -y skills add antonbabenko/deliberation --skill reload-mcp --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/reload-mcp
Context preview
The summary Claude sees to decide when to auto-load this skill.
Gracefully cycle dashboard and audit MCP processes after deliberation is updated.
SKILL.md
reload-mcp.SKILL.mdname: "reload-mcp" description: "Gracefully cycle dashboard and audit MCP processes after deliberation is updated."
<!-- GENERATED by scripts/sync-hosts.js - edit the source under prompts/, docs/tool-guide.md, or examples/, then regenerate. -->
Reload Deliberation MCP
Use this skill when Deliberation has been updated to cycle running background services and verify MCP worker states.
Instructions
Run the reload script to audit running processes and gracefully restart the dashboard daemon on the latest code:
bash scripts/commands/reload-mcp.sh
- Preserves active host stdio pipes to prevent broken pipe errors.
- Automatically cleans up orphaned worker processes.
- Gracefully restarts the dashboard daemon on the latest version.
- Next tool calls or new sessions will automatically resolve the updated code.
Get a second opinion from GPT, Gemini, and Grok in Claude Code, Codex, Cursor, Kiro, Antigravity, OpenCode, or any other MCP host - plus 400+ more models through OpenRouter, including Qwen, Kimi, and DeepSeek.
Repo: antonbabenko/deliberation
Other skills on deliberation.
code-reviewer
Find bugs, security holes, and maintainability issues in a diff or file.
deliberation
When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the…
researcher
Research external libraries, APIs, and best practices, with evidence.

