System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.
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 asgeirtj/system_prompts_leaks --skill antigravity_guidegit clone --depth 1 https://github.com/asgeirtj/system_prompts_leaksWrote 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/asgeirtj/system_prompts_leaks/antigravity_guide)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/antigravity_guide"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/antigravity_guide/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/asgeirtj/system_prompts_leaks/antigravity_guide"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/antigravity_guide.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 | $0.00112 | $0.00744 |
| Opus 5.5 | $0.00045 | $0.00298 |
| Sonnet 5.5 | $0.00022 | $0.00149 |
| Haiku 4.5 | $0.00011 | $0.00074 |
Grade A, and why
antigravity-guide 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 5d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Antigravity (AGY) Guide & Sitemap
Google Antigravity is an AI-first development platform. Depending on which
surface the user is asking about, you MUST read the corresponding
subdocumentation in the references/ directory of this skill:
1. Surfaces Sitemap (Offline Subdocs)
- Antigravity CLI (
agy): references/cli.md- Pointers to the authoritative public CLI docs for slash commands,
features, settings, and best practices.
- Pointers to the authoritative public CLI docs for slash commands,
- Antigravity IDE: references/ide.md
- Covers the standalone AI-first IDE, sidebar chat panels, and inline code
lenses.
- Covers the standalone AI-first IDE, sidebar chat panels, and inline code
- Antigravity 2.0: references/app.md
- Covers the parallel desktop application, left-hand sidebar, chat canvas,
and the HTML Auxiliary Pane (Subagents, Background Tasks, Artifacts,
Files Changed, Terminals).
- Covers the parallel desktop application, left-hand sidebar, chat canvas,
- Antigravity SDK: references/sdk.md
- Covers the public Python SDK
(https://github.com/google-antigravity/antigravity-sdk-python) for
programmatic agent leasing, orchestration APIs, and custom tool
exposing.
- Covers the public Python SDK
2. Smart Hybrid Retrieval: When to Fetch Live Docs
The offline subdocs provide excellent quick references. However, if the user
asks for the latest updates, advanced Vertex AI integrations, or complex setups
not covered here, you MUST dynamically fetch the live page from the official
sitemap:
- Main Documentation Home:
https://antigravity.google/docs - Skills:
https://antigravity.google/docs/skills - Rules:
https://antigravity.google/docs/rules-workflows - Hooks:
https://antigravity.google/docs/hooks - Plugins:
https://antigravity.google/docs/plugins - Sidecars:
https://antigravity.google/docs/sidecars - Model Context Protocol (MCP):
https://antigravity.google/docs/mcp - Browser Automation & Testing:
https://antigravity.google/docs/ide/browser - Agent Permissions & Security:
https://antigravity.google/docs/permissions - Terminal Sandbox:
https://antigravity.google/docs/sandbox - Changelog & Release Notes:
https://antigravity.google/changelog - Troubleshooting & Support:
https://antigravity.google/support
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.
- 5d ago First seen · 56 lines · 112 tokens per session scan A 73f1704dfa07
antigravity-guide is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,713 stars, last pushed yesterday), licensed CC0-1.0. It adds 112 tokens to every session and 744 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-30.
Other skills, from other repositories
concept-diagrams
Generate flat, minimal educational SVG visuals as HTML.
baoyu-comic
A creator for educational comics, including biographies and tutorials, that turns supplied content or topics into illustrated comic pages.
memento-flashcards
Spaced-repetition flashcards: create, review, quiz, export.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
canvas
Fetch Canvas LMS courses and assignments via API token.
build-interactive-explainers
A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.