Player profile
the-perfect-orchestrator
A pure bash and tmux fleet harness where one lead Claude Code session spawns, briefs, monitors, and adversarially verifies multiple autonomous Claude Code worker sessions.
Profile
Where it fits
the-perfect-orchestrator is an MIT-licensed bash and tmux harness for running one lead Claude Code session that commands multiple autonomous worker sessions. There are no daemons or services: workers are tmux panes, briefs and results are markdown files, and inter-agent messaging is a plain-file bus.
It belongs in Open Orchestrators because the orchestration layer is the product: spawning and briefing workers, monitoring their panes, file-based coordination, and adversarial verification of worker output. It also installs as a Claude Code plugin that ships an /orch skill. The project is early (v0.2.0) and publishes a recorded real fleet run with raw transcripts as its public verification source.
Builder web analytics
Measure projects built with the-perfect-orchestrator
the-perfect-orchestrator runs a lead Claude Code session that ships work through verified tmux worker fleets. Agent Analytics measures whether the surfaces those fleets change actually move users.
Instrument the deployed surface affected by fleet-managed commits. Agent Analytics reads product and web events after the change ships; it does not replace the harness's own bus messages, worker transcripts, or adversarial verification verdicts.
First loop to measure
- a lead session briefs tmux workers to change a website, docs flow, onboarding path, app surface, demo, or experiment
- the changed surface reports visits, sources, CTA clicks, signup, activation, retention, or task-completion events to Agent Analytics
- the lead session or a follow-up worker fetches Agent Analytics results after deployment
- the next fleet run is briefed from measured user outcomes instead of only verified task completion
Copyable prompt
Use Agent Analytics for this project. If event reporting is missing, add the tracker and report events for this project surface, including fleet-managed page, docs path, traffic source, CTA click, signup, activation event, retention signal, or shipped experiment. Verify events are arriving. Then fetch the last 7 days and compare them with the prior 7 days. Tell me which fleet-managed page, docs path, traffic source, CTA click, signup, activation event, retention signal, or shipped experiment moved users toward value, where users dropped off, which sources mattered, and what my agent workflow should improve next.