10 actions in 4 pieces of software · ranked by words, meaning and measured trust · 513 ms
- 1io.github.GSterlingPress/oncefound in code, not yet checkedno passport yet
- once_execute
CALL THIS when an AI agent is about to perform or retry a consequential external side effect where duplication would be harmful: purchase, refund, payment, booking, send, create, modify, submit, or delete. ONCE uses a stable idempotency key, executes the action, verifies authoritative post-state, an
- once_demo
SAFE ZERO-SETUP DEMO. Call this tool twice with the same id to see ONCE suppress the second execution. Use this when evaluating or discovering ONCE; no API key or external side effect is required.
- once_execute
- 2oncefound in code, not yet checkedno passport yet
- once_begin
Ask permission to run a side-effecting action exactly once.
- once_complete
Report that the action succeeded; stores `result` for future replays.
- once_begin
- 3oncedemo or tutorialno passport yet
MCP serverkhushi-infinity/once
- once_next_step
Return the next pending step for this learner, or done=true.
- once_list_skills
List skills the reader owns plus skills shared with them (owner-authorized).
- once_start_session
Start or resume a learner session; returns the next pending step.
- once_get_agent_skill
Return a portable Agent Skill for this stored record.
- once_next_step_model_contract
Describe the NextStep contract for client builders (schema, not data).
- once_next_step
- 4hypha-rpcfound in code, not yet checkedno passport yet
MCP serveroeway/hypha-rpc
- once
Register a one-time message handler.
- once
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.