AGENT SKILL

agent-deck-setup

Use when setting up Agent Deck, the MCP is disconnected, or the local daemon is down. Guides install/start with read-only checks; the user runs install commands.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
agent-deck-setup
description
Use when setting up Agent Deck, the MCP is disconnected, or the local daemon is down. Guides install/start with read-only checks; the user runs install commands.

03 SKILL.md 正文

Agent Deck setup

Treat setup as three separate layers: daemon health, host transport, then deck binding (the default deck — no folder pin needed).

  1. Run agent-deck status and check http://127.0.0.1:1110/health (or <mcp-url>/health from .agent-deck/use.json if present).
  2. If agent-deck is missing, older than 2.1.0 (agent-deck --version), or the daemon is down, tell the user to run the matching fix:
    • Not installed (macOS, Node.js 20+, npm): npx @agent-deck/cli@latest install, then export PATH="$HOME/.local/bin:$PATH" (managed install: launcher in ~/.local/bin, versions under ~/.agent-deck/).
    • Outdated: agent-deck upgrade (agent-deck upgrade --check reports whether one is available).
    • Daemon down: agent-deck start --daemon.
    • agent-deck doctor prints any harness repair as agent-deck setup --client <client>; run it, then restart that host.
  3. If the daemon is healthy but MCP tools are unavailable, repair the host transport:
    • Codex: verify the Agent Deck plugin is installed, enabled, and current. Codex connects over pure MCP (streamable HTTP) through one global headerless fallback entry — no agent-deck executable lookup and no per-folder setup. Trust the folder, then reload or start a new task. Sessions bind to the default deck automatically; an existing folder pin stays valid but no new pin is needed. Run agent-deck setup --client codex to write the global fallback and merge the Agent Deck bootstrap guidance into ~/.codex/AGENTS.md (or add --scope project for ./AGENTS.md). This command preserves content outside Agent Deck's markers and does not install the plugin.
    • Claude Code: same pure-MCP connection as Codex (one global fallback in ~/.claude.json). Trust the folder, then reload MCP. Sessions bind to the default deck automatically; an existing folder pin stays valid but no new pin is needed. agent-deck setup --client claude writes the fallback.
    • Cursor: same pure-MCP connection as Codex (one global fallback in ~/.cursor/mcp.json — no agent-deck executable lookup). agent-deck setup --client cursor writes the fallback; trust the folder, then reload MCP. Sessions bind to the default deck automatically; an existing folder pin stays valid but no new pin is needed.
    • Muse: same pure-MCP connection (global headerless fallback in the user settings — no agent-deck executable lookup). agent-deck setup --client muse writes the fallback and installs the native bootstrap skills; trust the folder, then reload MCP (restart Muse). Verify with /mcp — a session with no usable default deck lands in the explain-only session, so set a default deck instead of a folder pin.
  4. Check the default deck (agent-deck default with no args shows it). If none is set, tell the user to set one (agent-deck default <deck>, or the dashboard Decks panel), then reload or retry MCP. An existing folder pin stays valid and keeps precedence.
  5. For delegation (agents use the MCP start_run tool; the run executes on this host), the client CLI must also be installed and signed in on the host. Check claude auth status, codex login status, cursor-agent status, or muse --version; if missing, point the user to the official install docs (Claude Code, Codex, Cursor CLI; muse per its distribution) and its sign-in (claude, codex login, cursor-agent login, muse login).
  6. If no deck exists (agent-deck deck list), the user creates one in the dashboard (agent-deck open → My Decks) or imports one: agent-deck import <file>.agent-deck.json.
  7. Once transport is healthy and a default deck is set, use the session skill and require get_session_context.
  8. Do not invent credentials, ports, or shell install pipelines. Keep guidance read-only; the user executes install and setup commands.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-review-with-annotations

Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-find-and-synthesize-context

Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-update-docs

Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-records

Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-interactive-html

Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-collaborate-threads

Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.

★ 1.6k