opus 5.5 出来当天，我拿自己 11 个 repo 里的 22 个真实提交做了一轮 medium 对 high 的配对测试： 两档完成度一样，high 慢三分之一、多花三成多 token，但盲评里多抓出几个测试查不出来的真 bug。 再对一下 Artificial Analysis 的 Intelligence Index 数据，最后把默认档定成了 high。 文末按不同用法给了推荐。

On launch day I replayed 22 real commits from 11 of my own repos, running Opus 5.5 at medium and high effort side by side. Both finished every task; high took about a third longer and 35% more tokens, but blind judges credited it with catching several bugs the tests couldn't see. Cross-checked against the Artificial Analysis Intelligence Index, I made high my default. Recommendations by usage profile at the end.

上一篇让几个 claude 账号自己换着用，人还是拴在电脑前。这一篇把 agent 全挪到一台常开的机器上，手机随时连上去看进度、派新活，笔记本合盖它也接着跑。三个开源件各管一段——herdr 管 session、hcom 管通讯、Moshi 管手机——外加账号自动轮换兜底，凑成我目前跑得最顺的移动端 vibe coding 方案。这篇讲怎么搭，也讲踩过的坑。

Last time I taught a few Claude accounts to rotate themselves — but I was still chained to my laptop. This time I cut the last cord: the agents live on an always-on box, and my phone connects in to watch and steer them. Close the lid, leave the house, lie in bed — they keep running. Three open-source pieces each own one layer — herdr the sessions, hcom the messaging, Moshi the phone — plus account auto-rotation as the safety net. The mobile vibe-coding setup that currently runs smoothest for me: how to build it, and the traps I hit.

天天用 claude code 的人都撞过五小时用量墙，切号还要重新登录，正在跑的 session 也会丢。 我搞了两个工具：clauth fork 在活跃 session 底下做无感热切换和无人值守自动轮换， 菜单栏的 ccsbar 把每个账号的余量、预报和健康状况摆在明面上。这篇讲这套东西是怎么搭起来的。

I run several Claude accounts and kept hitting the 5-hour wall mid-session. Switching meant logging out. So I built a daemon that hot-swaps the active login under a running session — and the whole thing turned on one non-obvious fact about how macOS stores an auth token.

The reflex when an agent misbehaves is to add a sentence to CLAUDE.md. It's wrong in two directions: instruction files are context, not enforcement, so the rule won't bind under pressure — and the longer the file gets, the more it pollutes the context that makes the agent reliable. Load-bearing rules belong in hooks, lint, and CI. The prose should get shorter.

Agent 干错事，大多数人的反射是往 CLAUDE.md 加一句话。它错在两个方向：指令文件是 context 不是强制，规则在压力下根本不绑得住；而文件越长，越污染那个让 agent 可靠的 context 本身。承重的规则该进 hook、lint、CI，散文应该越写越短。

I wanted a sushi-counter field guide that used the names you actually order by in a US restaurant — not Latin binomials. So I pointed a team of agents at it: parallel research workflows verifying English menu names with web search, gpt-image-2 for ~150 photoreal neta shots, and a deterministic HTML→PDF assembler. 73 fish, 92 pages, two debugging war stories, and a free download.

朋友给我一份用拉丁学名的 omakase 认鱼课，可板前点菜时，菜单写的是 Hamachi、是 Sea Bream。我想要一个标美式菜单常用名的版本，于是指挥一队 agent 搭了出来：九个并行调研 agent 上网核实菜单名、gpt-image-2 出约 150 张写实图、一段确定性代码拼成 PDF。73 种鱼、92 页，外带两个踩坑故事和一份免费下载。

Six months of accumulated Claude Code configuration — 50 skills, 50 subagents, 40 commands, hooks, rules, and the sync pipeline that pushes all of it to a public GitHub mirror with a fail-closed two-tier audit. What's inside, why I built it, and the workflow philosophy behind it.

AX-skills is the public mirror of my personal Claude Code skills directory — eleven workflows for writing, research, image generation, knowledge sync, and one cyber half-immortal divination skill. After a year of writing them, I think a skill isn't a stored prompt — it's how you encode care.

同一条流水线——Claude Design 出方向、HANDOFF.md 锁死、`big-task` 落地——但每个产品都把它掰成不一样的形状。ÉLAN 是空地，需要宽探索。识川 app 已经上线，要按类目一个个迁移。盘盘猫是 monorepo，v2 跑三个并行品牌表达而不是一个方向。变的是什么，不变的是什么。

Solo dev 做设计，大多数时候 N=1——第一直觉就是唯一方案，因为做第二个版本要花一天。Claude Design 把这事拆了：一下午六个完全不同的视觉语言摆在面前。留下了什么、丢了什么、方向锁死之后 big-task 的 ui profile 接手怎么走——这篇讲这些。

先是裸跑 Claude Code。再是 GSD 多 agent 仪式。再是 superpowers 的 skill 库。最后在上面包了一个自己的 orchestrator。每一版崩盘都来自一个具体 session。最后我才想明白：solo dev 的 harness 跟团队的不是一个物种，而且真正的答案不是选一个默认引擎——是按工作形状路由。

Same pipeline — Claude Design explores, HANDOFF.md locks, `big-task` ships — but it bends around each product. ÉLAN is greenfield and needs wide exploration before converging. Shichuan has a live app and needs incremental category-by-category migration. Panpanmao is a monorepo with a v2 redesign that runs three parallel brand expressions instead of one. What changes and what doesn't.

For solo dev and small teams, design exploration is usually N=1 — you go with your first instinct because producing a second variant takes a day. Claude Design collapses that: six distinct aesthetic directions in an afternoon. What I kept from the pipeline, what I dropped, and how `big-task`'s UI profile takes over once a direction is locked.

Vanilla Claude Code. Then GSD's multi-agent ceremony. Then superpowers' skill system. Then a custom orchestrator on top. Each rewrite came from a specific session that broke. What I learned: solo dev harnesses and team harnesses are different species, and the right answer isn't a default engine — it's routing by work shape.

Shadow Access flips the found-phone genre: you're not investigating someone else's device — you're discovering what someone did inside yours. An iOS interface that slowly gets 'infected' as you uncover the intrusion.

Dead Signal is the second game — an investigative journalist reconstructing a murder victim's final 72 hours from fragmented phone data. The horror comes from data, not visuals.