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 save-as-standalone-htmlgit 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/save-as-standalone-html)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/save-as-standalone-html"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/save-as-standalone-html/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/save-as-standalone-html"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/save-as-standalone-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00014 | $0.01336 |
| Opus 5 | $0.00007 | $0.00668 |
| Sonnet 5 | $0.00003 | $0.00267 |
| Haiku 4.5 | $0.00001 | $0.00134 |
Grade A, and why
save-as-standalone-html 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- save-as-standalone-html — 95% identical, 17 lines differ
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save as standalone HTML
Export the current design as a single self-contained HTML file that works completely offline — no external dependencies.
How it works
There is a deterministic bundler (super_inline_html tool) that can inline resources referenced directly in HTML attributes — img src/srcset, source src/srcset, video/audio/track src, video poster, SVG <image href>/<use href>, link href (stylesheets, favicons), script src, CSS url() and @import, inline style attributes. However, it CANNOT discover resources that are only referenced as strings in JavaScript or JSX code — for example:
- An image src set in React:
<img src={"./hero.png"} /> - A background URL in a styled-component:
background: url('./pattern.svg') - A dynamically imported script
Your job is to prepare the HTML file so the bundler can capture everything, then run it.
Step 1: Make a copy of the HTML file and update code-referenced resources
Copy the current HTML file. Read it. Copy its dependencies. Look through ALL the code (inline scripts, imported JSX files, styled-components, etc) for any resource URL that is referenced as a string in code rather than as an HTML attribute. This includes:
- Image URLs in React/JSX (
<img src={...} />,style={{ backgroundImage: ... }}) - URLs in CSS-in-JS (styled-components, inline styles set via JS)
- Script tags that import other scripts which themselves reference resources
- Any fetch() or XMLHttpRequest calls that load assets
- Audio/video sources set programmatically
Note: if you use the Anthropic API in the project, it will not work standalone. If this is core to the project, STOP and tell the user!
Step 2: Add ext-resource-dependency meta tags
For EACH resource found in step 1, add a <meta> tag in the <head>:
<meta name="ext-resource-dependency" content="<url>" data-resource-id="<id>" />
Where:
contentis the URL of the resource (relative to the HTML file, or absolute)data-resource-idis a short, unique identifier (e.g. "heroImage", "patternSvg")
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.
- 12d ago First seen · 106 lines · 14 tokens per session scan A b9d46bb1bd57
save-as-standalone-html is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,893 stars, last pushed 2d ago), licensed CC0-1.0. It adds 14 tokens to every session and 1,336 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
pretext
Build creative browser demos with DOM-free text layout.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
inspecting-hermes-desktop-dom
Read the live Hermes desktop DOM/CSS over CDP.
impeccable
Frontend design guidance, upstream-maintained (impeccable).