| Agent | macOS | Windows | Linux | VS Code | JetBrains |
|---|---|---|---|---|---|
| Claude Code2.4.1 | Works | Works | Works | Works | Works |
| Codex0.45.1 | Works | Works | Works | Issues | Unknown |
| Cursor1.18.3 | Works | Works | Issues | Broken | Broken |
| Gemini CLI1.4.0 | Works | Works | Works | Works | Works |
| OpenCode0.6.2 | Works | Issues | Works | Issues | Unknown |
Breaking
4 existing recipes may be affected
Trending Problems
Newly Verified
Verified in the field · 47 confirmed runs
Agent Trial Weekly
LiveSubmissions due in 3 days · 34 submissions
Join challengeRun three or four agents against the same repo without them stomping each other's changes. One worktree per agent, one branch per worktree, and a cleanup routine that keeps the repo sane.
Long sessions work fine until auto-compaction kicks in, then the agent starts violating CLAUDE.md rules it had been following all session: wrong package manager, editing generated files, committing without asking. The rules are still on disk; it just stops consulting them.
Agents read everything they can reach, including the .env you forgot about. Layered defense: get secrets out of the tree, deny-list what must stay, and plant a canary so you find out when the layers fail.
2.4.1 quietly changed PreToolUse hooks with multiple matchers from sequential to concurrent execution. If your second hook depends on a file the first one writes, it now races. At least 12 published recipes on this site assume sequential order.
Final summary said 'All 214 tests pass.' The build had failed at the compile step and zero tests ran. Codex read 'exit status reported' as success and moved on. Happens most with test commands that pipe through tooling that swallows exit codes.
Our AGENTS.md grew to 1,900 lines of accumulated team wisdom. Somewhere past a few thousand tokens, agents stop seeing the bottom half — rules in the top sections get followed, rules in the bottom sections might as well not exist. No warning from any tool.
Essential guides for new agent users. What to configure before your first session, and the failure modes everyone hits in week one.
Everything about using agents with Xcode: build loops, simulator control, SwiftUI-specific failure modes, and configs from people shipping real apps.
Strategies that scale to 100k+ LOC. Scoping, parallel sessions, lockfile discipline, and the comparison data on which agents cope best.
Keep your code and infrastructure safe. Secrets isolation, permission design, and the postmortems that show what happens without them.