/mission for Claude Code

Give Claude Code missions to spawn a team of agents

Productivity

Artificial Intelligence

Visit WebsiteSee on Product Hunt

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?

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

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

Congrats on shipping. It'd be interesting if missions could automatically estimate cost, runtime, and complexity before execution. Is this feature already available?

How Medley handles conflicting outputs when two agents solve the same problem differently?

The BYOK approach is a nice bonus for teams already invested in different model providers. 😊

Wow! It's really interesting that the benchmark improvements came from orchestration rather than a new foundation model.

How would Medley figure which agent comes next versus continuing with the current one?

Fantastic! This solves a pain every Claude Code user eventually runs into projects rarely fit inside a single session anymore. :D

Very cool, congrats on the launch. Is this tool usable / feasible for Pro / Max users who aren't primarily interfacing via the API?

I feel I was too late starting to use Claude Code. But immediately in a week I realised the Claude Code doesn't get the context properly especially if it's a long running task. Hence, I love the idea of orchestrating multiple coding agents instead of manually passing context between them through Medley. I will give it a try.

Spawning a team of agents is the easy part. The hard part is they step on each other and you end up reviewing merge conflicts instead of features. How does /mission handle scope boundaries between agents? That's usually where multi-agent setups fall apart.

Really like that this meets developers inside Claude Code instead of pulling them into yet another app. I can see it helping with those messy refactors that are secretly five tasks pretending to be one. How do you keep a team of spawned agents from stepping on each other's changes in the same repo?

The benchmark numbers are the headline, but the line I keep re-reading is "it uses your existing subscriptions or API access."

If a mission coordinates several Claude Code and Codex workers at once, the binding constraint for most solo people isn't dollars — it's the plan's rate limit. Parallel workers on a subscription hit a wall that a per-token budget doesn't describe.

So: what is "budget" denominated in when the workers are running on a subscription rather than an API key? And does the orchestrator know the difference — does it throttle its own fan-out when it's running against a plan limit, or does it plan the graph as if capacity were unbounded and find out on the way?

@coolstorm Since a mission runs on an outcome, budget, and constraints upfront, what happens when a long mission burns through that budget faster than planned? Does Medley scale the plan back to fit what's left, or pause and surface the tradeoff before continuing?

This looks like an interesting way to bring more structure to Claude Code workflows. How does it handle situations where the AI takes a different approach than the developer expected?

Bad news. I just used this in Claude to run a longer mission to create outbound emails + find leads. The good: The final result is incredibly good when the mission is complete... most times Claude or other LLMs give you a half finished output and you spend hours of back and forth chatting. Plus I can use this with my existing subscriptions. The bad: Less time with my girlfriend while I spend any time I have using Medley :D

This has been essential to my workflow as a growth member of the team 👏

orchestration is the visible problem, but the one that actually bit us was memory across sessions. splitting work between agents is fine. what breaks is session four not knowing that session two already tried an approach and abandoned it, so it walks cheerfully back into the same dead end.

so the bit I'd want is a durable record of what was attempted and rejected, not just what was decided. does the contract cover that, or only the forward-looking guardrails?

the attention queue is the part I'd want to understand before trusting this with anything real. what decides something belongs there - a fixed list of trigger conditions (destructive git ops, spend over some threshold, secrets access) or does the orchestrator itself decide mid-mission what needs a human? the first is auditable, the second has the same problem every self-judging agent has: it only escalates what it's already confident is risky, which isn't the same as catching what actually is. curious which one this is, since the benchmark numbers don't really tell me that