The Five Days Between the iOS 27 RC and Release — I Check Init Order and Entitlement Restore Before Layout
A record of how I narrow the agent's search scope during the short window before an OS release — by launch path rather than by screen. Includes the audit script I run to catch consent and ads init ordering, entitlement restore gaps, and hardcoded size branches.
How much of Antigravity's generated commit message I actually keep
Where the Review pane's generated commit message stops being enough, and where I start writing. A prepare-commit-msg hook that adds a Why trailer, plus measured behaviour during rebase, cherry-pick and revert.
Why Filename Search Misses Every Error String in Your Repo
Antigravity 2.12 improved partial filename search. Measuring name lookups against full-text search across a 2,088-file repository, the reading cost differed by 67x and error strings hit filenames only 4.5% of the time. Here is where the line actually falls.
The work-root guard I run before letting an agent near several repositories
When several repositories share one machine, an agent's working root is remarkably easy to mix up. Here is a small guard that compares resolved paths, tested against seven inputs.
Git Tracks the File, but Your Agent Can't See It. Here's Where It Drops Out
An agent's code search returned two files. git grep returned six. I traced the three paths that quietly drop tracked files out of search, measured them on a synthetic repo and a production one, and worked out how to spot the gap in a single line.
The Cleanup Step Removed the Working Directory, Not Its Contents — Making Unattended Destruction Fail Closed
An unattended cleanup step deleted the working directory itself instead of what was inside it. Here is why the mkdir -p that followed was not a safety net, and how a defensive-looking default value ended up selecting the destructive branch, with the actual verification output.
Why I Check Description Overlap Before Turning On inheritCustomizations
CLI 1.1.14 collapsed markdown agent inheritance into a single inheritCustomizations switch. Here is what happened when I actually inventoried the 47 skills in my workspace and decided the switch on description overlap rather than on context size.
When Antigravity Swaps Its Default Model, Only the Jobs You Narrowed First Survive
Gemini 3.7 Flash is now the default model for Antigravity agents. The places you never configured are exactly the places that shift silently. Here is how to inventory your default-model exposure, then split your jobs into move-now and hold, scored by how much output freedom you left open.
Android 17 Went Canary-Only, So I Gave My Agent the Silence Rules First
Android 17 dropped Developer Previews in favour of rolling Canary builds, which moved the verification deadline onto my side of the table. Here is how I handed the tracking job to an Antigravity agent by designing when it stays quiet, not when it reports.
How Far to Narrow an Agent's Choices in a 30-Category Wallpaper Classification Pipeline
Asking an agent to pick one of 30 categories per image means re-running every image the moment a definition changes. Here is the reasoning and the implementation behind switching to closed-vocabulary tags plus a deterministic rule mapping.
A Typo in agent.md Quietly Widened My Permissions — Writing a Strict Frontmatter Lint
Misspelled keys in agent.md frontmatter do not raise errors. They fall back to defaults, and for permission fields that fallback points the wrong way. Here is the failure I hit, the lint I wrote to catch it, and what the measurements showed.
One Space in a Path, and Nine Commands Reported Success While Counting the Wrong Place
A single space in a workspace name sends agent-written commands somewhere else, quietly. Measurements across eleven unquoted-path forms, and the entry-point script that closes the boundary in one cd.