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 sparklingneuronics/sparkling-skills --skill agygit clone --depth 1 https://github.com/sparklingneuronics/sparkling-skillsWrote 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/sparklingneuronics/sparkling-skills/agy)<a href="https://agentmods.dev/skills/sparklingneuronics/sparkling-skills/agy"><img src="https://agentmods.dev/badge/skills/sparklingneuronics/sparkling-skills/agy/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/sparklingneuronics/sparkling-skills/agy"><img src="https://agentmods.dev/badge/skills/sparklingneuronics/sparkling-skills/agy.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 | $0.00263 | $0.04189 |
| Opus 5 | $0.00131 | $0.02094 |
| Sonnet 5 | $0.00053 | $0.00838 |
| Haiku 4.5 | $0.00026 | $0.00419 |
Grade A, and why
agy 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agy — delegate to Google Antigravity (multi-model)
Delegate a prompt to Antigravity's agy CLI and bring the result back. agy is Google's agentic CLI and the sanctioned successor to gemini-cli's individual tier (which Google deprecated) — it authenticates with a free Google account and routes to multiple models: Gemini 3.x, Claude Sonnet/Opus 4.6, and GPT-OSS. The user keeps Claude Code open while another model handles the side task.
When to use
Trigger on:
/agy <prompt>or/gemini <prompt>— explicit invocation- "ask agy …", "ask gemini …", "run agy …", "have antigravity …", "get agy's take on …"
- "check with agy", "validate with gemini", "see what agy thinks" — generic delegation; you infer the topic (the user won't name it)
- second opinions / parallel checks on anything — code, and non-coding: "have agy review this email", "see what gemini thinks of this plan"
- "continue with agy", "resume with gemini", "/agy resume" — resume the matching conversation (see Topic-aware sessions)
- "use agy to create an image / illustration of X", "have gemini illustrate this" — image generation, only when agy/gemini is named (see Images)
Naming the tool picks the model (see Parameters):
- "gemini" → a Gemini model (this is the gemini-cli replacement path)
- "agy" / "antigravity" → agy's default (Gemini 3.5 Flash), or a model you name
- "with Claude Opus / Sonnet", "a Claude take via agy" → that Claude model
- "with GPT" → GPT-OSS
Do NOT trigger for:
- Anything where the user wants Claude itself to do the work ("you write it", "don't delegate this")
- delegation aimed only at Codex (
/codex— "ask codex …"). A request naming both codex and agy/gemini triggers both skills; handle the agy portion here. - A bare request with no tool named — "review my PR", "create an image" — naming the tool is how the user chooses one
- The homonyms — "my partner's a Gemini" (the zodiac sign), "does anti-gravity exist in physics" — these name no tool
- Questions about agy or its setup, not delegations to it — "explain antigravity's permission model", "help me install / sign in to agy", "how do I run agy interactively"
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 172 lines · 263 tokens per session scan A 2d7d9364fd7e
agy is a skill published in the GitHub repository sparklingneuronics/sparkling-skills (6 stars, last pushed 3d ago), licensed MIT. It adds 263 tokens to every session and 4,189 once invoked, about $0.0013 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
improve-code-quality
Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…
refactoring-patterns
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when…
team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
reviewer
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /agy:reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier…
review-responder
Use when receiving feedback on code you implemented, responding to reviewer comments, deciding which review suggestions to implement, or pushing back on incorrect review feedback.