Snapshot Your Agents' Effective Scope So You Notice the Day a Default Changes
Antigravity 1.1.25 made Markdown-defined custom agents inherit the surrounding skills, rules, and subagents by default. Here is the snapshot-and-diff routine I now use to check whether an agent I meant to keep narrow quietly got wider after an update.
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.
A dependency without musllinux wheels doesn't fail on Alpine. It just gets slower
On Alpine, a dependency without musllinux wheels can quietly fall back to pure Python. Protobuf went from 0.043ms to 36.2ms, and pip reported no error.
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.
Why I took the show-or-not decision away from every dialog
A paywall prompt, a review request and a rewarded-ad confirmation landed on the same frame. Here is how I moved the show-or-not decision out of each dialog into a single gate, how I rewrote the agent instructions as invariants, and how a CI check keeps it that way.
Before You Narrow the Page Range in Antigravity 2.11.0, Find Your Resolution Floor
I measured the new page range and MediaResolution options in view_file against a 240-page document. Resolution moved the numbers more than the page range did, and setting it too low drops words without raising a single error.
What @ Includes Actually Shrink When You Split Agent Rule Files
I split my rule files using Antigravity 2.11.0's @path/to/file includes and measured the before and after across four real repositories. Maintenance surface dropped 62 percent. What a session actually reads dropped 1.7 percent. Here is why, plus the code that catches the silent failure mode.
A Green Build Is Not Proof That Your pbxproj Edit Was Correct
When an agent edits project.pbxproj, the build stays green while resources and script phases quietly fall out. Four structural checks and an audit script that finishes in 0.1 seconds on a 1,200-file project, drawn from running iOS apps in production.
Three things I had to fix before my status line could tell me what a session cost
Getting real session cost into a custom Antigravity CLI status line took three fixes: how the script reads stdin, how to tell whether your build sends a cost field, and how to keep a usage ledger that does not double-count.
Building a Verification Loop With Antigravity 2.10.0's Embedded Terminal
Antigravity 2.10.0 puts a terminal in the sidebar. Here is how I pinned my pre-merge checks down to three commands, scoped them to changed files only, and what the measured difference turned out to be.