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 Dannykkh/skill-olympus --skill antigravitygit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/antigravity)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/antigravity"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/antigravity/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/dannykkh/skill-olympus/antigravity"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/antigravity.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 | $0.00054 | $0.00500 |
| Opus 5 | $0.00027 | $0.00250 |
| Sonnet 5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
antigravity 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 7d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Antigravity CLI
Google Antigravity CLI is the Google command-line runtime. Gemini remains a model family; do not invoke the retired gemini executable.
Workflow
- Verify the runtime with
agy --version. If it is unavailable, report that Antigravity CLI must be installed or repaired; do not fall back togemini. - Run
agy modelswhen model choice matters. Use a currently listed model and never hardcode a preview model from memory. - Give Antigravity a bounded prompt that names the files, question, required evidence, and output format.
- Prefer read-only review. Grant write or command permissions only when the user asked Antigravity to modify or execute something.
- Capture the result, verify actionable claims against the repository or tests, and distinguish Antigravity findings from confirmed facts.
Headless usage
agy -p "Review the authentication flow. Cite file:line evidence and list only actionable findings." --output-format json
Optional controls:
--model <id>: choose an ID returned byagy models.--effort <level>: tune reasoning effort when supported by the selected model.--output-format text|json|stream-json: select machine-readable output for automation.--continueor--conversation <id>: resume an existing Antigravity conversation.
Use a timeout supplied by the host runner for background jobs. Never use obsolete Gemini CLI flags such as --approval-mode, --sandbox, --yolo, or -i.
Permission boundary
Use Antigravity's configured permission policy for routine automation. --dangerously-skip-permissions bypasses safety prompts and is allowed only when the user explicitly authorized unrestricted tool execution for that run. A request for review or analysis alone is not that authorization.
Result contract
Return:
- the model ID used, when explicitly selected;
- the useful findings or recommendation;
- which claims were independently verified;
- any timeout, authentication, permission, or parse failure.
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.
- 7d ago First seen · 47 lines · 54 tokens per session scan A 4e56583aa5f7
antigravity is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 500 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 2026-09-03.
Other skills, from other repositories
project-audit
Repository audit for non-website projects (CLI, libs, backend, monorepo). Use when: "project-audit", "project audit", "repo audit", "code audit".
adversarial-review
Critical review (min. 5 findings). Modes: code, audit, plan. Use when: "review", "critical review", "code review", "plan review", "audit review".
inline-review
Quick self-review checklist after code changes. Lightweight alternative to adversarial-review. Use when: "review my changes", "self-review", "quick review", "check my work", or automatically after significant edits.
review-team
Launch parallel code review agents for comprehensive multi-perspective review. Use when: "review team", "full review", "multi-review", "review-team".
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…
factory-code-reviewer
Use to review a PR, diff, or recently-written code against the factory's conventions. Read-only — outputs structured review, not diffs. Carries the full factory-pitfalls digest as a PR checklist plus the conventions from every other factory-.md skill. Flags anti-patterns, missing conventions, security risks, and…