Problem
Claude Code2.4.0
5
2h ago
Problem
by Anthropic · latest 2.4.1 (Jul 31, 2026)
Anthropic's command-line coding agent. Runs in the terminal, IDE extensions, and a desktop app; strong at multi-file edits, long-running tasks, and following repository instructions — with some sharp edges around context compaction and hook execution that this community tracks closely.
Codex is fast and overshoots; Claude is a pedantic reviewer. Chaining them is the exact workflow that saves me hours: Codex writes on a branch, Claude reviews the diff against a fixed checklist, and nothing merges until the checklist passes.
Long sessions die one of two deaths: the bill or the compaction. This is the freelancer's version of token discipline — measure per task, keep the context lean on purpose, and checkpoint state to files so a fresh session costs you minutes, not the afternoon.
In a 400k-line workspace, an unscoped agent burns half its context discovering packages it will never touch — then edits one it shouldn't. Run the agent from the package directory, deny writes outside it, and hand it the workspace-level commands it still needs.
Claude Code can't see Xcode's build errors unless you hand them over. XcodeBuild MCP plus a formatter that strips the noise gives the agent a real edit-build-test loop for SwiftUI work — the difference between guessing and iterating.
Server components by default, one blessed data-fetching pattern, and hard rules about 'use client'. This file exists because every one of those rules was violated by an agent first.
Twelve years of Rails opinions distilled for an agent: fat models within reason, no service-object cargo cult, bin/rails test as the heartbeat, and migrations treated like the loaded weapons they are.
Same 12 tasks I run on every release. Fable took 9, Opus took 2, one tie — but the interesting part isn't the score.
Four ways to run the same agent. Which one should someone actually start with, and why?
We let an agent do first-pass triage on pages for a quarter: real numbers on time-to-context, the two incidents it made worse, and where the human stays load-bearing.
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.
Compaction ate my constraint again. Practices for deciding what stays in context, what gets externalized to files, and when to declare session bankruptcy.