Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add airvalona/antigravity-like-claude-code --skill verifygit clone --depth 1 https://github.com/airvalona/antigravity-like-claude-codeWrote 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/airvalona/antigravity-like-claude-code/verify)<a href="https://agentmods.dev/skills/airvalona/antigravity-like-claude-code/verify"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/verify/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/airvalona/antigravity-like-claude-code/verify"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00055 | $0.00405 |
| Opus 5 | $0.00028 | $0.00202 |
| Sonnet 5 | $0.00011 | $0.00081 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
verify scanned grade A with 0 findings 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/verify — Implementation Verification
Port of Claude Code's bundled verify skill. Meant to be run as a final check
before calling a task finished, distinct from debug (which is for chasing
down a known problem) and code-review (which is a style/quality pass).
Steps
-
Restate the original ask in one line to confirm scope — what was actually requested, not what got built (these can drift).
-
Run the real checks:
- Run the project's test suite if one exists and is relevant to the change
- Run the actual command/flow the user described, if it's something that can be exercised directly (start the server and hit the endpoint, run the CLI command, render the component, etc.) — don't just read the code and assume it works
- Check edge cases implied by the request (empty input, error paths, boundary values) even if not explicitly listed
-
Compare against the original ask point by point. If the request had multiple parts, verify each one was actually addressed — partial completion presented as done is worse than flagging what's left.
-
Report status honestly:
- If everything checks out: say so plainly, list what was verified
- If something's missing or broken: say exactly what, don't soften it or bury it under what did work
Notes
This skill exists to catch the gap between "the code looks right" and "the code was actually confirmed to work." Prefer running something over reasoning about whether it would probably work.
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.
- 8d ago First seen · 39 lines · 55 tokens per session scan A 6354dd746bcb
verify is a skill published in the GitHub repository airvalona/antigravity-like-claude-code (2 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 405 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.