/mission for Claude Code - Give Claude Code missions to spawn a team of agents
by•
Medley is a free Claude Code plugin for work bigger than one session. Type /mission to turn an outcome into a live graph, coordinate Claude Code and Codex workers, review the result, and keep going. BYOK via OpenRouter for Kimi, GLM, and more.
Replies
Wow! It's really interesting that the benchmark improvements came from orchestration rather than a new foundation model.
Spine
@krutiparekh16 Thanks Kruti! Exactly — a lot of the recent work on multi-agent systems and harness engineering is about taking already-capable models, working around their weak spots, and getting more out of their strengths. That's the direction we studied, and we built a harness that pushes the models' capability higher.
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 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?
@rickwise following up since i haven't seen an answer to this one yet, and it's the part i'd actually worry about more than the token budget. if two workers hit a rate limit at the same moment, does the mission queue and retry, or does one worker's failure just look like a task failure to the reviewer with no signal that it was capacity and not a real error? that distinction is basically the whole question of whether "keeps going" holds up on a subscription plan instead of an API key
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.
Very cool, congrats on the launch. Is this tool usable / feasible for Pro / Max users who aren't primarily interfacing via the API?
GrowMeOrganic
Fantastic! This solves a pain every Claude Code user eventually runs into projects rarely fit inside a single session anymore. :D
How would Medley figure which agent comes next versus continuing with the current one?
The BYOK approach is a nice bonus for teams already invested in different model providers. 😊
Nas.com
How Medley handles conflicting outputs when two agents solve the same problem differently?
TestMu AI
Congrats on shipping. It'd be interesting if missions could automatically estimate cost, runtime, and complexity before execution. Is this feature already available?
Spine
@syed_shayanur_rahman This is often hard to do given task complexity and model costs and latency vary quite a bit. The planner can do a rough estimate for most tasks where there is no emergent work.