Antigravity Skill Vault is a collection of reusable Agent Skills for Google Antigravity, covering software development, operations, security, and business work. It is for people who want Antigravity agents to follow specialized expertise, personas, and structured workflows. The catalogue skills are entries from this collection.
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 rmyndharis/antigravity-skills --skill antigravity-skills-managergit clone --depth 1 https://github.com/rmyndharis/antigravity-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/rmyndharis/antigravity-skills/antigravity-skills-manager)<a href="https://agentmods.dev/skills/rmyndharis/antigravity-skills/antigravity-skills-manager"><img src="https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/antigravity-skills-manager/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/rmyndharis/antigravity-skills/antigravity-skills-manager"><img src="https://agentmods.dev/badge/skills/rmyndharis/antigravity-skills/antigravity-skills-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00049 | $0.01154 |
| Opus 5 | $0.00024 | $0.00577 |
| Sonnet 5 | $0.00010 | $0.00231 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
antigravity-skills-manager 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 13d 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.
- All underlying commands must use standard Python library features (`urllib.request`, `json`, `os`, `sys`) without third-party dependencies. How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📦 Antigravity Skills Manager (rmyndharis/antigravity-skills)
The antigravity-skills-manager skill empowers Google Antigravity agents and users to discover, search, install, and manage over 300+ agent skills from the open-source repository rmyndharis/antigravity-skills.
Use this skill when
- Searching or exploring available agent skills in the
antigravity-skillscatalog. - Installing a new skill into the global Antigravity configuration directory (
~/.gemini/antigravity/skills/<skill_id>/). - Listing locally installed skills to check system capabilities.
- Managing skill updates or auditing active agent tools.
Do not use this skill when
- Performing general domain coding tasks that do not involve discovering or managing skills.
- Working on tasks outside the scope of Antigravity skill management.
Instructions
- Prefer the
/skills-manager(or/skills) slash commands. They work wherever the plugin is registered and need no path resolution. skills_cli.pydoes not sit next to this file. Installing this skill copies onlySKILL.mdinto the skills directory; the script lives at the root of the checkout or npm package it came from —agy plugin installclones the repo, so it is at the clone root, and the npm package puts it atnode_modules/@rmyndharis/antigravity-skills/skills_cli.py. Locate it before invoking it, and run it from there;python3 skills_cli.py <cmd>from this skill's own directory will not find it.- If neither the repo nor the npm package is on disk, use
npx @rmyndharis/antigravity-skills(theag-skillsCLI) instead — it covers the same four operations. - Ensure skill installations save to
~/.gemini/antigravity/skills/<skill_id>/SKILL.md, or toAG_SKILLS_DIRwhen that is set. - All underlying commands must use standard Python library features (
urllib.request,json,os,sys) without third-party dependencies.
Safety
installwrites instructions that every future Antigravity session loads automatically. Confirm the skill id with the user before installing, and show them whatsearchreturned rather than picking on their behalf.installreplaces an existing installation of the same skill id, discarding local edits under that directory. Say so before overwriting.- Never install a skill id the user did not ask for, and never install one that is absent from the catalog.
installwrites under the resolved skills directory —AG_SKILLS_DIRwhen set, otherwise~/.gemini/antigravity/skills. Report the exact path back to the user rather than assuming the default.
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.
- 13d ago First seen · 101 lines · 49 tokens per session scan A 2911c9db80ac
antigravity-skills-manager is a skill published in the GitHub repository rmyndharis/antigravity-skills (1,529 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,154 once invoked, about $0.0002 per session on Opus 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
code-review
Systematic code review skill covering both requesting a review (pre-commit checklist) and receiving and responding to review feedback. Checks code quality, security, test coverage, architectural alignment, and documentation before any code is committed.
writing-plans
TÜRKÇE AÇIKLAMA ─────────────── Bu skill, onaylanmış bir scope veya fikirden somut, uygulanabilir bir implementasyon planı üretir. Hangi dosya değişecek, hangi sırayla, kim yapacak, ne kadar sürecek, hangi riskler var — hepsini netleştirir. Planın çıktısı doğrudan executing-plans veya dispatching-parallel-agents…
brainstorming
TÜRKÇE AÇIKLAMA ─────────────── Bu skill, bir fikir veya problemi Sokratik yöntemle rafine eder. Agent sana cevap vermez — sorular sorar. Bu sorular aracılığıyla fikrin netleşir, varsayımlar sorgulanır, kapsam belirlenir ve gerçek ihtiyaç ortaya çıkar. "Ne yapalım?" sorusunu "Tam olarak ne yapmamız gerekiyor ve…
project-context-primer
Run this skill at the very start of any new conversation or agent session before writing a single line of code. It loads the project's architectural decisions, conventions, known gotchas, and current task status so the agent operates with full context — not as a blank slate.
test-driven-execution
Before writing any implementation code, define the acceptance criteria and test cases that the code must satisfy. Agents then write code to pass these tests — not to match a vague description. Eliminates "it works on my machine" and "I think this is what you wanted" outcomes.
idea-validator
Structured validation framework that scores product ideas. Use when evaluating problem severity, willingness-to-pay, or founder-market fit. For market intelligence, see market-research.