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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaksnpx agentmods add skills/asgeirtj/system_prompts_leaks/storybookWrote 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/storybook)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/storybook"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/storybook/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/storybook"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/storybook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 16 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]
- medium MCP Rug Pull · line 19 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]
- medium MCP Rug Pull · line 42 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]
- medium MCP Rug Pull · line 45 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 | $0.00000 | $0.16334 |
| Opus 5.5 | $0.00000 | $0.06534 |
| Sonnet 5.5 | $0.00000 | $0.03267 |
| Haiku 4.5 | $0.00000 | $0.01633 |
Grade A, and why
storybook 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 1mo 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storybook source shape
Storybook is the fidelity oracle, not the runtime. The converter bundles the package's compiled dist/ into _ds_bundle.js - the same bundle the claude.ai/design agent builds with - and generates each preview by compiling the story source module itself (hooks, fixtures, local helpers - the whole closure comes along), with every component import resolved to that shipped bundle (lib/story-imports.mjs redirects package and relative component imports to window.<Global>). The repo's own storybook render is the ground truth those previews must match: a compare harness screenshots each story in the reference storybook and the matching preview render side by side, and you iterate until they match. Nothing from storybook-static is uploaded, and no story code is ever evaluated at build time - stories run only in the browser, against the real artifact.
Requires React 18+. Playwright + chromium are required for this shape (the compare loop is the verification), not optional.
First sync or re-sync? A re-sync is marked by a config whose projectId and pkg were both in place before this run started - most of this document then doesn't apply; go to §7, where one driver run routes the work and untouched components cost nothing. Everything else takes the full flow (§2 build -> §3 self-heal -> §4 match -> conventions header (base SKILL.md, before upload) -> §6 upload), where every component gets verified and graded once - that includes a partial config left by an aborted run, and a pin this run itself just recorded in the base skill's §1. (Only the old design-sync.config.json present? Move it first and commit: mkdir -p .design-sync && mv -n design-sync.config.json .design-sync/config.json, then apply the same test.)
2. Build, then run the converter
- Build the DS package and its workspace dependencies. The converter bundles
dist/intowindow.<Global>. Run<pm> run build; in a monorepo useturbo run build --filter=<pkg>orpnpm -F "<pkg>..." build(the trailing...is required - bare-F <pkg>skips dependencies and you'll seeCannot find module '@scope/tokens'). Ifpackage.jsonmodule/exports['.']points at TS source, find the actual built entry and pass it via--entry. Do this before step 2 - storybook often imports sibling packages from their builtdist/. - Build the reference storybook ONCE into
.design-sync/sb-reference/- NOT underds-bundle/(the converter wipes--outon every rebuild, and storybook builds take minutes; the reference must survive the fix loop):
What ships with it
3 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.
- 1mo ago First seen · 341 lines · 0 tokens per session scan A 25714b54d589
storybook is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,707 stars, last pushed 2d ago), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 16,334 tokens. 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
gsap-web
GSAP in a React or Next.js app without the leaks -- timelines over stacked tweens, useGSAP and context for cleanup, ScrollTrigger set up so it survives route changes and layout shifts. Use when building GSAP animations in a component-based app.
list-components
List all React component files (.tsx, .ts, .jsx, .js) in the components folder.
comps-analysis
Build comparable-company valuation workbooks in Excel.
anatomy
Explain an idea as an interactive isometric machine figure.
pretext
Build creative browser demos with DOM-free text layout.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.