discover

1# Discover
2 
3Internal procedure for `evo:discover`. The user only sees the user-facing prompts, the dashboard URL, and the baseline score -- everything else is the agent's choreography.
4 
5## Evo surface
6 
7General guidance on the skills and tools available in evo. Each line is a triggering condition: if you're about to do X, pull/dispatch/read this. Don't preload -- act when the trigger fires.
8 
9**Always have a sense of the skill before jumping into its references.** A skill body carries the decision-making; references are concrete contracts that assume a decision has been made.
10 
11```
12evo plugin
13│
14├── Main thread  (the orchestrator -- you, inside /evo:discover or /evo:optimize)
15│   │
16│   ├── Skills (Skill tool)
17│   │   ├── evo:discover       starting a new evo workspace / instrumenting a project
18│   │   ├── evo:optimize       after discover commits the baseline -- drives the loop.
19│   │   │                      Args: subagents=N (read sizing-the-round FIRST),
20│   │   │                            autonomous, subagents-only, budget=N, stall=N
21│   │   ├── evo:ship           after the loop stops -- distills the best valid
22│   │   │                      experiment into a mergeable change (PR if remote,
23│   │   │                      else merge) + a mergeability report
24│   │   ├── evo:finetuning     task is finetuning / post-training / training a model
25│   │   └── evo:infra-setup    need a remote backend, pooled workspaces, lease/slot
26…