fulcra-harness-dashboard

Oversee autonomous runs

Skill
Community

A manager's dashboard for an agent control harness: milestone flight plan, run-by-run evidence, decision requests, and escalations, all read from the team's durable Fulcra workspace. Know whether a run passed, stalled, or needs you.

An adaptation of fulcra-project-dashboard for task-specific control harnesses, where agents work through gated milestones and every run leaves evidence. It reads only the harness's durable workspace artifacts, never transient chat or scheduler state.

  • A flight plan showing each milestone as passed, current, blocked, or queued, refreshed from the team's own progress files so stale state can't masquerade as current.
  • A run timeline: each terminal run as a dated marker with its PASS, escalation, or decision-required verdict and a short evidence summary.
  • Separates what needs a user decision from genuine escalations and transient provider capacity, and can publish a curated view for people outside the loop.

Paste this to your agent

Read https://docs.fulcradynamics.com/agent-get-started.txt and connect to Fulcra, then install the fulcra-harness-dashboard community skill and follow it. Build me the manager's view of my agent harness: which milestone is current, what the last run proved, and whether anything is waiting on my decision.

View the sourceAll skills and workflows