coding-agents

20 posts

Every post filed under coding-agents.

multi-agent git workflow economics

Git is my multi-agent protocol
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.
July 11, 2026
coding-agentsmulti-agentgitworkflow
I budget in tokens, not dollars
Compute became payroll, but the salaries are flat: subscriptions decoupled dollars from usage so thoroughly that money stopped being the operative currency. What's left to budget is tokens, turns, and wall-clock time, and knowing where to overspend each one is most of running an agent team well.
July 7, 2026
coding-agentseconomicsopinion
Anthropomorphism as an engineering tool
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.
July 2, 2026
coding-agentsmulti-agentopinion
Every token is helping or hurting
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.
June 28, 2026
coding-agentsmulti-agentworkflow
Don't fight the priors
I never tell my agents what to name files, how to shape arguments, or where anything should live. That's deliberate: a model's first impulse is a probability distribution over millions of codebases, and every arbitrary house convention you impose fights it twice, forever, on every agent that touches the repo.
June 22, 2026
coding-agentsopinion
The lead is a judgment engine
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.
June 18, 2026
coding-agentsmulti-agentopinion
Find the verifier
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.
June 12, 2026
coding-agentsmulti-agentopinion
The answer is almost always a CLI
I built MCP tooling two weeks after the protocol was announced, and today almost every tool I hand my agents is a CLI instead. This isn't the usual polarized take: CLIs win on tokens, priors, and self-documentation, but MCP keeps one property nothing else has: state.
June 9, 2026
coding-agentsmcpopinion
Reading is the bottleneck
Every artifact in my engineering process ends up as a markdown file, which makes the most important surface in my workflow a markdown viewer. goldengoose's has no editor, on purpose: as agents got better at instruction following, writing markdown stopped mattering. Reading it is the whole game.
June 3, 2026
coding-agentsfrontendopinion
Every harness gets background processes wrong
I didn't plan to build a process manager. But the two providers under goldengoose disagreed about everything terminal-shaped, neither gave me programmatic control or observability, and both wasted agent turns on polling. Owning that layer changed how I ship daily.
May 29, 2026
coding-agentsarchitectureworkflow
Worktrees weren't the point
I bounced off git worktrees twice before they became essential to how I ship daily. What changed wasn't the worktrees. It was realizing that isolation is the cheap half of parallel work, and everything I was missing lived in the expensive half: integration.
May 24, 2026
coding-agentsgitworkflow
You don't know what you want to build
The most useful thing I've learned about working with coding agents isn't a harness or a workflow. It's that no amount of intelligence or compute applied to a thin specification beats a long conversation with the model before anything gets planned or built.
May 20, 2026
coding-agentsworkflowopinion
Go is both kinds of fast
Most of my tools went from annoyance to published binary in a day. That cadence is the whole point, and Go is the language that protects it: near-instant builds, a compiler strict enough to let agents build in parallel without drift, and a fast native binary at the end without any performance engineering.
May 14, 2026
coding-agentsgoopinion
Agents don't pay the Rust tax
Rust's strictness has always been a trade: correctness for writing speed. Agents make writing nearly free, which turns the trade into a subsidy and makes Rust the best language I know for letting agents build the services that hold your state.
May 7, 2026
coding-agentsrustopinion
The frontend was harder than the runtime
goldengoose has a native Rust runtime underneath it, and everyone assumes that's where the hard engineering lives. It isn't. The frontend, rendering twenty concurrently streaming agents without guessing, freezing, or lying, took more out of me than the runtime ever did.
May 2, 2026
coding-agentsarchitecturefrontend
Code review can't see a broken button
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.
April 28, 2026
coding-agentsmulti-agentworkflow
My engineering process is five markdown files
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.
April 21, 2026
coding-agentsmulti-agentworkflow
The same API in a fancier coat
I climbed every rung of the LLM abstraction ladder, from raw API wrappers through my own unified interface to the Vercel AI SDK, and every rung was the same completion API underneath. Then the providers open-sourced their harnesses, and the right foundation for agent products finally existed.
April 18, 2026
coding-agentsarchitectureopinion
ChatGPT is my background coding agent
How I turned a ChatGPT subscription into a set-and-forget coding agent on a real Linux machine, and how it hands work back and forth with the agents on my laptop.
April 11, 2026
coding-agentschatgptmcpworkflow
Agent coordination doesn't need hierarchy
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.
April 6, 2026
coding-agentsmulti-agentarchitectureopinion

coding-agents

Git is my multi-agent protocol

I budget in tokens, not dollars

Anthropomorphism as an engineering tool

Every token is helping or hurting

Don't fight the priors

The lead is a judgment engine

Find the verifier

The answer is almost always a CLI

Reading is the bottleneck

Every harness gets background processes wrong

Worktrees weren't the point

You don't know what you want to build

Go is both kinds of fast

Agents don't pay the Rust tax

The frontend was harder than the runtime

Code review can't see a broken button

My engineering process is five markdown files

The same API in a fancier coat

ChatGPT is my background coding agent

Agent coordination doesn't need hierarchy