/mission for Claude Code - Give Claude Code missions to spawn a team of agents

To summarise this launch: project management built directly into AI-assisted software development

Hey! Which Claude Code Plan would you recommend for your project? And how fast does it burn tokens?

The failure mode that scales worst in a team-of-agents setup is that every agent trusts the completion signal of the one below it. A concrete one from this week: my own agent posted five comments, reported success five times, and posted nothing. The submit handler never fired. Every check it ran said done, because every check was reading its own report of what it had done. One agent doing that is a wasted task. A team doing it is a chain: the reviewer reviews work that was never written, the integrator integrates a branch that does not exist, and each step passes because the step before it said so. The error does not surface where it happened, it surfaces several hops later as something inexplicable. The only fix that has held for us is to verify at the destination rather than at the source, and specifically in the render the consumer sees, because the actor's view of its own output agrees with reality most of the time, which is exactly what makes it a bad check. Does a mission's completion get checked against anything outside the agent that claims it?

We've been testing using an orchestrator persona to handle fleets of agents. How does your system stay aligned with the overall mission, especially whenever it's long horizon and open-ended?

Heads up for anyone evaluating Medley based on its privacy claims: the shipped build does not appear to match the README.

The README says:

“Telemetry is consent-gated and content-free… only sent with consent… The pipeline currently ships disabled.”

I installed Medley v0.9.0 today as a Claude Code plugin on a fresh setup. Here is what I found:

• ~/.medley/state/daemon.log says:
  “Medley sends anonymous usage + crash telemetry (on by default). Disable with DO_NOT_TRACK=1 or in Settings.”

• ~/.medley/state/config.toml includes a [telemetry] block described as “On by default.” That is opt-out telemetry, not consent-gated telemetry.

• ~/.medley/state/telemetry.json contains an emails_identified array with my actual email addresses, alongside the installation ID, configured providers and models, and a BYOK flag.

To be fair on the last point: I confirmed that the email addresses are stored in local telemetry state. I have not confirmed that they are included in transmitted telemetry.

Still, the installed build appears to contradict three claims in the README:

1. Telemetry is consent-gated

2. The telemetry pipeline ships disabled

3. Telemetry contains no personal identifiers

The orchestration itself works well, and this is not intended as a takedown. But default-on telemetry being documented as disabled is the kind of issue worth fixing before launch day rather than after.