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 design-systemgit 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/design-system)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/design-system"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/design-system/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/design-system"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/design-system.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 | $0.00048 | $0.04398 |
| Opus 5.5 | $0.00019 | $0.01759 |
| Sonnet 5.5 | $0.00010 | $0.00880 |
| Haiku 4.5 | $0.00005 | $0.00440 |
Grade A, and why
design-system 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 28d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System — a system made from the shared type
This artifact is one release of the Design System runtime: index.html, this
SKILL.md and artifact-type/. A design system is an ordinary artifact that serves them
read-only and keeps its content in ITS OWN FILES under project/; icons and images sit in its asset store, named by the
index. A system inherits the type's capabilities
{"artifact":{},"downloads":{},"user":{"scopes":["profile"]},"assets":{},"comments":{"composer_only":true,"customAnchors":true},"room":{},"db":{"rules":[{"path":"","write":"admin"}]}}
and contract "0.2.47". Writes need Can edit; a
session without it says so, no retries.
Write only under project/: everything else is the type's (refused).
A system kept in files
Its index is project/design-system.json, nothing else, holding a createdOnFiles or
convertedFrom object, the marker (read it first; no project/design-system.json: an empty
system, see Creating; for a clean-up, stop and say so):
{"v":3, "layout":"files", "createdOnFiles":{"v":1,"at":"2026-09-14T18:20:00Z"}, "title":"Acme", "namespace":"Acme", "libraries":[{"name":"react","version":"18"},{"name":"react-dom","version":"18"}], "sections":{}, "groups":["Logos","Icons"], "assetGroups":{"Logos":{"name":"Logos","tile":"l","order":[],"files":{}}}, "blobs":{}, "docs":{"readme":"project/README.md","sections":[]}}.
"editing": "off" in the index turns off editing on the page; it, or a source entry not marked upgraded, has the page offer a clean-up ("Finish the migration"). Asked for one in words, not by its button, first ask if they want its files reorganized into this format. Then do so by Revising. Files the format has no place for (kits, some foundations pages) stay put. Keep authors' words; add nothing in their voice. Pictures, fonts and scripts stay files, moved where format.md puts them, paths repaired: upload none, inline none, whatever else these pages say. Remove files only as (craft.md: Move aside) says; name any you could not. Remove editing and source in the LAST call, once files follow format.md. Other changes are just made, both kept.
Everything under assets/<Group>/
that is not text (icons, logos, images, SVG too, video, PDF) is an asset upload,
named by a record assetGroups.<Group>.files.<file>: {"name", "blob": "<id>", "size", "type"}:
name = its path below the group folder (acme-mark.svg), the key the same with bytes outside
[A-Za-z0-9_./-] written ~ + two hex; <id> from the /_blob/<id> the upload returned; size in
bytes; type its media type. A group's order lists those names in tile order; groups orders the
groups. Leave sections, blobs and docs to the page (new index: {}, {}, {"sections":[]}).
To revise: ONE publish whose files holds only the project/ paths you changed; no
capabilities, contract. The
index goes ONCE, in the LAST call of your work, never in the small calls before it (a call
replaces the whole file: a copy read earlier would undo a rename, or drop the record of an icon a
person added meanwhile): read it right before, change those (its lastChange and the keys your
change touches: title, libraries, an asset record), keep every other key and the marker. A system YOU start (no index yet) gets project/design-system.json
with createdOnFiles exactly so, at = now. A project/design-system.json with no marker
is not an index: the page opens read-only; say so, write nothing over it.
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.
- 28d ago First seen · 211 lines · 48 tokens per session scan A f7978a94b2a8
design-system is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,884 stars, last pushed 2d ago), licensed CC0-1.0. It adds 48 tokens to every session and 4,398 once invoked, about $0.0002 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 2026-10-10.
design-system compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-systemasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 48 | Claude Code, Codex |
| anatomyNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 15 | Claude Code, Codex |
| claude-designNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 16 | Claude Code, Codex |
| tldraw-offlineNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 19 | Claude Code, Codex |
| ip-as-logoNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 16 | Claude Code, Codex |
| mono-colorNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 15 | Claude Code, Codex |
| scrollcraftNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 13 | Claude Code, Codex |