haiggoh/claude-code-desktop-sync
Plugin Claude Code
Keeps MCP-server config in sync between Claude Code and Claude Desktop via a SessionStart hook, and reports the manual steps for anything that can't be auto-synced.
haiggoh/claude-code-desktop-sync
Hook
Runs when a session starts, running python3. From haiggoh/claude-code-desktop-sync.
haiggoh/claude-code-desktop-sync
Skill Claude CodeCodex
Manage and troubleshoot MCP-server sync between Claude Code and Claude Desktop. Use when the user wants to sync now, check what is/isn't syncing between the two apps, add or mirror an MCP server, diagnose why a server or the GitHub connector isn't showing up in Claude Desktop, or understand what can and can't be…
Plugin Claude Code
A subagent inherits none of your durable rules — not your CLAUDE.md, not your memory, not your installed-plugin nudges — so it can blindly violate one it never heard of. brief-agents scans all three layers into one compact /.claude/agent-briefing-index.md (auto-regenerated when the sources change) and nudges you to br.
Hook
Runs when a session starts, executing brief-check.py via python3. From haiggoh/brief-agents.
Hook
Runs before the agent uses a tool for Agent, Task and Workflow tool calls, executing brief-pretool.py via python3. From haiggoh/brief-agents.
Skill Claude CodeCodex
Use when you are about to delegate work to a subagent (the Agent or Workflow tool) for anything involving architecture decisions or writing code, and you want it to respect the durable rules THIS session knows but a fresh subagent does not. Invoke when briefing a subagent, when the agent-briefing index looks stale or…
Plugin Claude Code
Run a queue of open work to completion unattended: triage it into do-now / heavy / gated tiers, execute the autonomous pile without stopping between items, and close out with a gated list saying why each remaining item was left. Includes an autopilot orchestrator and a narrow attended pass that removes blockers …
Hook
Runs when a session starts, executing nudge.sh via bash. From haiggoh/run-to-completion.
Skill Claude CodeCodex
Use when the user asks to run a whole queue of open work unattended — "autopilot", "run everything you can", "clear what you can while I am away", "full auto on my open items". Orchestrates the complete run as an explicit checklist: triage the queue into tiers, execute the autonomous pile without stopping, then close…
Skill Claude CodeCodex
Use WHEN an unattended run is ending: the autonomous pile is exhausted, a resource limit is close, or the user has called a stop. Reconcile the durable records the run touched, stop cleanly at the gated boundary instead of churning, and write a wrap that says why each remaining item was left and how to resume it. Do…
Skill Claude CodeCodex
Use DURING an unattended run, once triage has produced a do-now pile: keep moving without stopping between items, switch away the instant something needs a human, protect against irreversible edits before touching a file, and carry each shippable change through to confirmed-live. Do NOT use for choosing what to work…
Skill Claude CodeCodex
Use when the work already in view in THIS conversation is an elaborate multi-step plan or spans several open projects AND most of the needed information is gathered, or when the user signals "autonomous" / "continuous" / "full auto" / "run to completion" / "keep going without stopping". Proactively offer to execute…
Skill Claude CodeCodex
Use BEFORE starting an unattended run, to score an existing queue of open items — a to-do list, an issue tracker, plan steps, or a persistent open-items store — into what is safe to do now, what is autonomous but heavy, and what is gated on a human. Produces a tier verdict plus a gate reason per item, and ranks the…
Skill Claude CodeCodex
Use when the user wants to work THROUGH the blocked items on a queue with you present — "unblock these", "walk me through what is gated", "let us clear the questions" — or immediately after an unattended run reports items it could not do. Turns each gate reason into the single question that would release the item…