Every post filed under multi-agent.
Before goldengoose had a team-status card, the lead drew one in Markdown. Turning that repeated report into deterministic UI gave the model and me one runtime-owned view of the team.
My lead can absorb feature requests all day because every agent works in a clean worktree and hands back an exact commit range. The underrated command is cherry-pick: it lets the lead replay approved histories onto a disposable candidate, test the combination, and keep main out of the mess.
My agents have names, roles, DMs, onboarding, and a rule about going home before they get sloppy. Treating them like colleagues isn't sentimentality; it's the cheapest, most reliable interface into both the model's training and my own management instincts. The skill is knowing where the metaphor pays rent and where it lies.
Two context-engineering features I built into goldengoose: compaction notifications routed to whoever created the agent and a context gauge any teammate can read. Then there is the planning habit that makes them rarely necessary: scope phases like context is the currency, and bias under-scoped.
The one agent I talk to all day never writes code. It delegates, schedules, integrates, and makes the judgment calls no benchmark measures. After living with this workflow daily, I think Claude models are post-trained into something specifically suited for that role.
The most useful thing I ever learned about prompting wasn't a prompting technique: it was understanding how frontier models are post-trained with reinforcement learning. Models are raised chasing verifiable objectives, which means any knowledge-work task becomes tractable if you can put a verifier in front of the goal.
My RPI pipeline ends with a reviewer clearing the diff, but a diff can't tell you the modal opens behind the header. So for web apps I added a stage after review: an agent that opens a browser, uses the feature like a person, and files what it finds back to the implementers.
Every non-trivial feature I ship goes through a research → plan → implement pipeline run entirely by agents. The whole process is five markdown files in .agents/skills, and the weird rules in them are the interesting part.
Everyone keeps answering 'how do agents coordinate?' with more hierarchy: spawn trees, sub-agents, orchestration layers. After building a multi-agent coding product, I think the answer is two primitives and a flat org chart.