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.
Reading the Same History in 38 Seconds — or 0.4: Handing a Read-Only .git to Your Agent
Antigravity CLI 1.1.10 lets the sandbox read .git without write access. I built a per-session history summary two ways, measured a roughly 100x speed gap, traced it to process spawn cost, and added a guard for shallow clones that silently corrupt the numbers.
I Copied the Same agent.md Into Another Repo and It Quietly Did a Different Job
CLI 1.1.6 lets you carry agent definitions around as files. I dropped one definition into eight repos, built a preflight that resolves its declared capabilities before the agent runs, and measured it against a naive checker.
Routing /effort by Task Class in Antigravity CLI: Six Weeks of Measurements
I built a small router that picks an /effort level from the shape of the task, then aggregated six weeks of run logs. Here is where raising effort helped, where it actively hurt, and what mattered more than effort.
The night my agent shipped nothing: giving generation agents an abstain outcome
When you score a background generation agent by how much it produces, the quality gate quietly loosens over time. Here is a three-valued ACCEPT / ABSTAIN / REJECT design that counts a zero-artifact run as a success, with the code and the measurements from running it.
Treating Code Search as a Contract: Measuring the /codesearch Regex Default
Antigravity CLI 1.1.3 interprets /codesearch queries as regular expressions by default. I measured the gap between regex and literal matching across a 979-article repository and turned the results into three query rules and a drift harness.
I Changed One Line in AGENTS.md and Broke the Agent — Regression-Testing the Instructions Themselves
Every time you edit the instructions you hand an agent — AGENTS.md, skill text — some other task quietly breaks. Here is a regression harness whose subject is the instructions, not the code: fixed tasks, deterministic assertions, and a way to wire it into unattended runs.
Handing Off IDE Work to the Chat Agent: Passing Context Through a File After the Two-App Split
Since Antigravity 2.0 split into an IDE and a chat-style agent app, context you build up in one does not carry into the other. Here is a file-based approach that makes a single file in your repo the source of truth for handoff, with a schema, a validation script, and a way to pin it with a Guide skill.
Faster Substring Search Changes How You Should Let Agents Explore Code
The 6/26 update made substring search noticeably faster. Rather than treating it as a comfort improvement, here is how to redesign the way agents explore code, budget context, and verify their targets, with measurements from indie development.
Running Xcode 27's Agent and Antigravity Side by Side: Designing the Work Boundary for iOS
With Xcode 27 bringing agentic coding into the IDE itself, iOS development now has two code-writing agents over one repository. Here is a practical design for keeping a single source of truth and splitting work across spec, implementation, and verification.
Stop Letting Antigravity Agents Self-Report 'Done' — Completion Contracts and External Verification
An Antigravity agent reporting 'done' when the work was not actually finished is a failure mode I kept hitting. Moving the completion decision out of the agent and into code fixed it. Here is the contract, a three-layer verifier, and how it holds up under unattended, scheduled runs.
Giving AI Agents an Aesthetic Sense — Building a UI Quality Evaluation Pipeline with Antigravity × Gemini Vision
Explore how to encode the vague judgment of 'is this UI good or bad' into code. Combines Antigravity with Gemini Vision to implement a complete pipeline — from screenshot capture to AI evaluation, improvement suggestions, automated fixes, and CI/CD integration.