This is awesome! I have a slight case of tritanopia in one eye and it was neat to see the difference. My boundary is bluer by 59% in one eye and 87% in the other. It tracks with what I would have expected.
My biggest problem with CC as a harness is that I can't trust "Plan" mode. Long running sessions frequently start bypassing plan mode and executing, updating files and stuff, without permission, while still in plan mode. And the only recovery seems to be to quit and reload CC.
Right now my solution is to run CC in tmux and keep a 2nd CC pane with /loop watching the first pane and killing CC if it detects plan mode being bypassed. Burning tokens to work around a bug.
I'm 3 weeks into switching from CC to OpenCode, and in some ways it is far superior to CC right out of the box, and I've maybe burned $200 in tokens to make a private fork that is my ultimate development and personal agent platform. Totally worth it.
Still use CC at work because team standards, but I'd take my OpenCode stack over it any day.
I find OpenCode vastly superior. Only thing missing is Vim mode but I saw a fork that someone implemented it. I really like being able to click on a previous message I sent to revert to that point in the conversation. You can revert in CC by pressing Escape twice but the “menu” it takes you to for picking the message is terrible because it only shows your messages. Also, expanding subagent/tools/thinking/etc. blocks is super intuitive in OpenCode whereas CC’s view when you press CTRL+O is also terrible and hard to understand at first glance.
I've got to do some cleanup before sharing (yay vibe coding) but the big things I've changed so far:
1) Curated a set of models I like and heavily optimized all possible settings, per agent role and even per skill (had to really replumb a lot of stuff to get it as granular as I liked)
2) Ported from sqlite to postgresql, with heavily extended schema. I generate embeddings for everything, so every aspect of my stack is a knowledge graph that can be vector searched. Integrated with a memory MCP server and auditing tools so I can trace anything that happens in the stack/cluster back to an agent action and even thinking that was related to the action. It really helps refine stuff.
3) Tight integration of Gitea server, k3s with RBAC (agents get their own permissions in the cluster), every user workspace is a pod running opencode web UI behind Gitea oauth2.
4) Codified structure of `/projects/<monorepo>/<subrepos>` with simpler browserso non-technical family members can manage their work easier (agents handle all the management and there are sidecars handling all gitops transparent to the user)
5) Transparent failover across providers with cooldown by making model definitions linked lists in the config, so I can use a handful of subscriptions that offer my favorite models, and fail over from one to the next as I hit quota/rate limits. This has really cut my bill down lately, along with skipping OpenRouter for my favorite models and going direct to Alibaba and Xiaomi so I can tailor caching and stuff exactly how I want.
6) Integrated filebrowser, a fork of the Milkdown Crepe markdown editor, and codemirror editor so I don't even need an IDE anymore. I just work entirely from OpenCode web UI on whatever device is nearest at the moment. I added support for using Gemma 4 local on CPU from my phone yesterday while waiting in line at a store yesterday.
Those are the big ones off the top of my head. Im sure there's more. I've probably made a few hundred other changes, it just evolves as I go.
I literally have a Claude Code skill called "/delib" that takes takes in any nodejs project/library and converts it to a dependency-less project only using the standard library.
It started as a what-if joke, but it's turned out to be amazing. So yeah, npmjs.com is just reference site for me now, and node_modules stays tiny.
And the output is honestly superior. I end up with smaller projects, clean code, and a huge suite of property-based tests from the refactor process. And it's fully automatic.
It varies from project to project, but applications benefit a lot more than libraries. When I de-lib a normal express app it might add a few hundred lines of code and a few thousand new tests, but if I de-lib an library then depends on how ancient it is. The older the library is, the higher the chances that most of what it needs is built-in to the standard library.
Thank you. I have been thinking about the same approach. However my worry is the open source libraries often gets more eyeballs and CPU cycles and ends up much more refined over a period of time.
I'm about 2 days into transitioning, using MiMo V2 Pro in place of Opus and MiniMax M2.7 in place of Sonnet.
I'm finding that the extra "hand holding" that MiMo and MiniMax need isn't really "extra." The Anthropic models happily agree to a plan and then do something else entirely way too often.
With MiMo and MiniMax I'm just spreading the attention throughout the day instead of big spikes of frustration figuring out where Claude went off the rails.
Thank for responding. So you are using MiMo V2 Pro to plan and then asking MiniMax M2.7 to read that plan file and execute? Or how the workflow looks like?
Pi/Opencode/Kilocode?
Just curious.
I am using Opencode mostly and thinking to abandon Copilot so looking for something similar.
Sorry for late reply, but yeah that's how my workflow looks, but I'm also more just leaning on MiMo V2 Pro now, it's fast, and cheap enough. And I'm using OpenCode.
For my particular monitor, that’s most of what I would use on i3 due to size limitations. The issue for me is that splitting the screen in OSX is so clunky compared to i3.
I use Hammerspoon and I have got a modal dialog that I summon with alt-space. This shows me the keys I can press next, and some of them are to move the current window to specific positions and sizes, such as 100% of the height and 80% of the width, on the right hand side.
It's not the same thing as a tiling window manager, but I actually like it better: I can use the 80%x100% size for my browser and keep a terminal on the left hand side. Then I can browse HN while still watching the terminal for output. When there is output in the terminal, that's a trigger for me to switch.
We operate as a diversion program with our local department of juvenile justice, and I would definitely describe the process as transformative.
From the financial perspective alone, our local law enforcement has seen a 6:1 return on investment on restorative practices. The value of all the changed lives is immeasurable.
reply