switchboard
Copilot instructions215 starsChanged 2 months agoMITView on GitHub
This project uses the Switchboard protocol for cross-IDE agent collaboration. You have access to these tools:
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- improve-featureSkill
- improve-planSkill
- external-team-leadSkill
- improve-featureSkill
- kanban-operationsSkill
- manage-featuresSkill
- query-kanbanSkill
- switchboard-orchestrationSkill
- worktree-cleanupSkill
- kanban-operationsSkill
- manage-featuresSkill
- query-kanbanSkill
- switchboard-cloudSkill
- switchboard-memoSkill
- switchboard-remoteSkill
- switchboardSkill
- worktree-cleanupSkill
The file
Files
Switchboard Configuration for Github
This project uses the Switchboard protocol for cross-IDE agent collaboration.
Available Workflow Tools
You have access to these tools:
Messaging (Cross-IDE)
- get_team_roster — Discover registered terminals/chat agents and role assignments.
Workflow Management
- start_workflow — Begin a workflow (e.g.,
improve-plan,accuracy). - get_workflow_state — Inspect active workflow and phase state.
- complete_workflow_phase — Mark a workflow phase as done (enforces step ordering and required artifacts).
- stop_workflow — End the current workflow.
Terminal Management
- run_in_terminal — Send commands to a registered terminal.
- set_agent_status — Update terminal/chat status.
- handoff_clipboard — Copy staged handoff artifacts to clipboard.
Workflow Triggers
| Trigger | Workflow | Description |
/improve-plan | improve-plan | Deep planning, dependency checks, and adversarial review |
/accuracy | accuracy | High-accuracy solo mode |
/switchboard-chat | switchboard-chat | Product Manager consultation (no code) |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.