AG Kit is a toolkit that gives Google Antigravity coding agents a structured workspace with rules, skills, specialist agents, workflows, persistent memory, orchestration, MCP guidance, and a safety hook. It is for building and operating agent workflows in Antigravity, and its catalogue entries provide parts of that workspace contract.
Borrowing it
Nothing to install: this file belongs to vudovn/ag-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vudovn/ag-kit/main/.agents/skills/verify-changes/SKILL.mdgit clone --depth 1 https://github.com/vudovn/ag-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vudovn/ag-kit/verify-changes)<a href="https://agentmods.dev/skills/vudovn/ag-kit/verify-changes"><img src="https://agentmods.dev/badge/skills/vudovn/ag-kit/verify-changes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vudovn/ag-kit/verify-changes"><img src="https://agentmods.dev/badge/skills/vudovn/ag-kit/verify-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00918 |
| Opus 5.5 | $0.00015 | $0.00367 |
| Sonnet 5.5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
verify-changes scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:3000/api/endpoint Copies of this mod
1 near-identical copy found in the catalogue:
- verify-changes — 88% identical, 153 lines differ
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Changes — Prove Code Works
"Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution.
Core Principle
❌ Verification by inspection: "I can see the function exists, it should work"
❌ Verification by assumption: "The types check out, so it's correct"
✅ Verification by execution: "I ran it, here's the output, it works because [evidence]"
Verification Protocol
Step 1: Identify What Changed
- Which files were modified?
- What behavior should be different now?
- What was the original bug/requirement?
Step 2: Determine Verification Method
| Change Type | Verification Method |
|---|---|
| Bug fix | Reproduce the original bug scenario → confirm it no longer occurs |
| New feature | Run the feature → confirm expected output |
| Refactor | Run existing tests → confirm nothing broke |
| API change | Call the endpoint → confirm response shape |
| UI change | Render the component → confirm visual output |
| Config change | Load the config → confirm values applied |
| Build/infra | Run build command → confirm success |
Step 3: Execute Verification
# For Node.js projects
npm run build # Does it compile?
npm run test # Do tests pass?
npm run dev # Does it start?
# For specific files
node -e "require('./path/to/module'); console.log('✅ Loads correctly')"
# For API endpoints
curl http://localhost:3000/api/endpoint
# For scripts
python script.py --test
Step 4: Report Evidence
## Verification Report
### What was changed
- [File list and summary]
### How it was verified
- [Exact commands run]
### Evidence
- Build: ✅ Compiled without errors
- Tests: ✅ 42/42 passing
- Runtime: ✅ Server starts, endpoint returns expected JSON
- Edge case: ✅ Empty input handled correctly
### Not yet verified
- [Anything that couldn't be tested automatically]
Verification Checklist by Project Type
Web Application
-
npm run build— compiles without errors -
npm run lint— no linting errors -
npm run test— all tests pass - Dev server starts successfully
- Changed pages render correctly
- No console errors in browser
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 129 lines · 38 tokens per session scan A a4ab56f9b3e8
verify-changes is a skill published in the GitHub repository vudovn/ag-kit (8,199 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 918 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.