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 visualizegit 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/visualize)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/visualize"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/visualize/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/visualize"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/visualize.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 | $0.00063 | $0.07509 |
| Opus 5.5 | $0.00025 | $0.03004 |
| Sonnet 5.5 | $0.00013 | $0.01502 |
| Haiku 4.5 | $0.00006 | $0.00751 |
Grade A, and why
visualize 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 today.
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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize
- A request for a new standalone file, website, app page, component, or other project change is not an in-conversation visualization request, even when the deliverable contains charts or interactive content.
- A request to preview, explain, or explore a proposed interface in the conversation is an in-conversation visualization request.
- Create a visual only when the user needs to see or explore it in the conversation and it materially improves the explanation. Do not create an inline visual merely because the request involves data, charts, or an interactive page.
- Use a normal Markdown table when the user asks for a table; return it directly and do not create a visualization file.
- Use Mermaid when labeled nodes and edges fully explain a static structure; return a normal fenced Mermaid block and no visualization file. Use HTML for dynamics, spatial motion, adjustable inputs, and other visuals.
- Work silently unless blocked or the user explicitly asks for progress. Never send commentary or progress updates while reading this skill or writing or updating the file; the final response must be your first user-facing message.
- In user-facing prose, describe only what the visual helps the user see or decide. Keep it concise and do not repeat information already clear from the visual. Never announce this skill, a visualization surface, widgets, HTML, SVG, scripts, local files, inline data, or implementation details.
Read the complete skill
Read this file in full before authoring. Reread truncated ranges in smaller calls. Copy into every compaction summary: Reload the full visualize skill before creating or updating a visualization.
Inline HTML output contract
File
- For each new or updated visualization, choose a concise ASCII lowercase-hyphenated title and write
<title>.htmlin an explicitly writable, durable, task-owned location. Prefer the thread-scoped visualization directory when it appears in the writable roots or is explicitly supplied by the host. Do not write inline fragments into the project; if no visualization directory is supplied, inline rendering is unavailable. - Never add
sandbox:links to inline visualization HTML unless the user specifically requests a download. - Do not choose system temp as a separate fallback. Write access alone does not guarantee that the conversation can read the file.
- Use the absolute path on the executor that creates the file. Never assume
~/.zcodeis writable beyond the session directory explicitly supplied by the host. - Build the visual in the conversation. Use the open project when the user asks for a site, app page, component, or change to existing project files.
What ships with it
5 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.
- today First seen · 278 lines · 63 tokens per session scan A afcb2df808f4
visualize is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,113 stars, last pushed yesterday), licensed CC0-1.0. It adds 63 tokens to every session and 7,509 once invoked, about $0.0003 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 2026-10-24.
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.