17 Dead References in My Handover Docs Turned Out to Be 2 Files, and the Real Risk Was a Different Site's Playbook Mixed In
The full Python script I use to check the root .md files an agent reads. My naive version counted 17 dead references; fixed, it was 7 across 2 files. Then it missed the real problem. Here is how I found it.
Turning a Page With No Declared Charset Into UTF-8 Before the Agent Reads It
A report says ReadURL can end an agent run with a UnicodeDecodeError. Here is a 60-line standard-library Python script that detects the charset and hands the agent clean UTF-8.
Hooks Load but Never Run — Isolating the Antigravity CLI 1.2.x Report with a Three-Line Canary
A reported problem in Antigravity CLI 1.2.1 and 1.2.2: hooks load and show up in /hooks, yet no hook process ever starts. Here is a three-line canary setup that tells a config mistake apart from an executor problem.
Before Handing an Agent a .zip: Dropping .git Cut 29 MB to 15 MB, and 28 Secret Warnings Turned Out to Be Noise
Antigravity app v2.23.0 lets you attach a .zip. I packed my own repository to count what .git weighs and how many secret-scan warnings are false alarms, and I leave the full Python script that excludes, scans, and writes a manifest.
Turning Gut-Feeling Judgments into Rules an Agent Can Actually Follow
A small, repeatable way to turn the judgment calls that live only in your head into written rules an Antigravity agent can apply, with a quick check against past cases.
The Image Model Shuts Down on October 29 — Find Every Call in Your Agent Setup and Cut Over with a Way Back
The Gemini API deprecations table lists a shutdown date of October 29 for the image model gemini-3.1-flash-image. Here is how I locate every call scattered across configs and code, match them to a ledger, and fix a cutover date and a fallback in advance — with scripts that run.
A Small Guard Script That Catches an Unattended Agent Rewriting Its Own Settings
After reading a report of an agent widening its own read-only limits by editing settings.json, I wrapped my overnight headless runs in an outside guard. Before/after fingerprints, quarantine and restore, and a hard timeout, with working code.
When an agent ends without a reason, I check the page's character encoding first
A page handed to ReadURL can end an Antigravity agent with nothing but Agent execution terminated. Here is how I tell those pages apart before handing them over, and why I now fetch and re-encode first.
When the iOS 27 Date Landed, the First File I Grepped Was AGENTS.md
iOS 27 and iPadOS 27 ship on September 14. Old version numbers linger in your source, but also in the files only your agent reads. Here is a script that counts both zones, plus the one line keyword search will never find.
Before I accept what /boost says it verified, I count what its throwaway worktree never saw
Antigravity's /boost runs its tests inside an ephemeral isolated worktree. If your build reaches for files git never tracked, that verification passed on a different tree than yours. Here is how I measure the gap first.
With scheduled agents, I now look for runs that never happened before I look for failures
My run ledger showed a 100% success rate while the evening slot had not fired for two weeks. Here is the reconciliation I now run against an expected-fire table, with measured notes on cron expansion, exit codes, and how the ledger itself gets written.
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.