Fable 5 vs Opus 5 in Claude Code: early numbers and vibes
Same 12 tasks I run on every release. Fable took 9, Opus took 2, one tie — but the interesting part isn't the score.
Claude Code2.1.2208 repliesField note1h ago
Field notes
Build logs, postmortems, trials, and open questions. The good parts get promoted into the answer pages.
12 field notes
Why does my Claude Max usage run out so fast in Claude Code?
The single most-commented complaint on the tracker, and mostly not a billing bug — it's what long context plus wide tool use costs. Here's what actually moved the needle for people.
Claude Code2.1.2207 repliesField note3h ago
Gemini CLI sits for an hour on a small edit — has anyone actually solved this?
A long-running report with a lot of theories and few confirmed fixes. Collecting what has and hasn't worked, honestly labelled.
Gemini CLI0.53.13 repliesField note5h ago
Anyone running OpenCode against local models for real work?
Not benchmarks, not demos — daily driving. Qwen3 Coder on a 4090 versus the API bill: where local actually holds up, where it quietly fails, and the routing setup that makes it viable.
OpenCode1.18.116 repliesField note7h ago
Codex is burning tokens very fast — what's a normal spend per task?
Hundreds of people report the same thing and almost nobody posts numbers. Here are ours, and what we found when we went looking for the cause.
Codex0.146.04 repliesField note7h ago
What actually belongs in CLAUDE.md?
Mine grew to 600 lines and the agent ignores most of it. Time to talk about what earns a slot in the most expensive real estate in your repo.
Claude Code2.1.2207 repliesField note8h ago
AGENTS.md or CLAUDE.md — is there actually one standard yet?
The most-requested Claude Code feature by comment count. If you use more than one agent, you are currently maintaining the same instructions two or three times.
All agents5 repliesField note10h ago
How are you actually sandboxing coding agents?
Every agent has a different permission model and none of them stop a determined `bash`. What people are running in practice, from nothing at all to full containers.
All agents5 repliesField note14h ago
How do you actually review a 4,000-line agent PR?
The agent worked for two hours and produced something plausible everywhere. Rubber-stamping is negligence, line-by-line is a full day. What's the actual workflow?
All agents9 repliesField note15h ago
Build log: a billing portal in one week with Claude Code and Codex
Five days, two agents, one working Stripe billing portal: what was delegated, what broke, what it cost ($61.40 all-in), and the day everything went sideways.
Claude Code2.1.2197 repliesBuild log3d ago
Build log: rewriting our iOS widgets, day by day
Eight days migrating a legacy widget suite to WidgetKit with Claude Code and XcodeBuild MCP: timeline budgets, a haunted pbxproj, and $84 of tokens.
Claude Code2.1.2185 repliesBuild log4d ago
Postmortem: production API keys in an agent-authored PR
An agent debugging a staging failure copied a .env file into a test fixture; the PR shipped to a public repo. Keys revoked in 71 minutes. The scanner that should have caught it was configured to ignore fixtures.
Cursor3.117 repliesFailure report1w ago