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-syncgit 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-sync)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/design-sync"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/design-sync/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-sync"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/design-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 63 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00056 | $0.06366 |
| Opus 5 | $0.00028 | $0.03183 |
| Sonnet 5 | $0.00011 | $0.01273 |
| Haiku 4.5 | $0.00006 | $0.00637 |
Grade A, and why
design-sync 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 11d 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:
- design-sync — 97% identical, 113 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync a design system to claude.ai/design
What this is for
Claude Design (claude.ai/design) is Claude's design tool: users prompt a design agent and it builds working UI - screens, flows, prototypes - rendered live in the browser from real React code. Out of the box it designs with generic components. This skill changes that: it converts the user's design-system repo into the format Claude Design consumes and uploads it, so from then on the design agent builds with the customer's actual components - every design it produces is on-brand, made of their real parts, and maps 1:1 onto code their engineers can ship.
That framing should drive every judgment call in this skill, because each uploaded artifact is an input to that agent (or to the humans steering it):
| Uploaded artifact | Consumed by | For |
|---|---|---|
_ds_bundle.js + _vendor/ |
the design agent's runtime | every design it produces renders these real compiled components from window.<globalName>.* |
styles.css, fonts/, tokens/, _ds_bundle.css |
every rendered design | the look - tokens, fonts, and component styles, all reachable from styles.css's @import closure (designs receive only that closure) |
<Name>.d.ts (<Name>Props) |
the design agent | the API contract it codes against |
<Name>.prompt.md |
the design agent | its usage reference - how to compose the component, with examples |
<Name>.html preview card |
humans in the component picker | how they find components and trust the sync |
_ds_sync.json |
future syncs | the sync anchor - content hashes that let a re-sync (any machine) skip re-verifying unchanged components AND compute exactly what to upload/delete |
This is why fidelity is the whole game: a component that renders wrong here renders wrong in every design the agent ever builds with it, and a wrong .d.ts or misleading .prompt.md makes the agent misuse the API everywhere. The verification loops in the sub-skills exist because of this - they are not bureaucracy.
What ships with it
26 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.
- design-sync.skill 218 KB
- lib/bundle.mjs 15 KB runs code
- lib/common.mjs 12 KB runs code
- lib/css-fallback.mjs 5.3 KB runs code
- lib/css.mjs 8.2 KB runs code
- lib/detect.mjs 1.4 KB runs code
- lib/docs.mjs 13 KB runs code
- lib/dts.mjs 29 KB runs code
- lib/emit.mjs 37 KB runs code
- lib/preview-gen-storybook.mjs 6.8 KB runs code
- lib/preview-rebuild.mjs 16 KB runs code
- lib/previews.mjs 9.4 KB runs code
- lib/remote-diff.mjs 13 KB runs code
- lib/source-kit.mjs 7.3 KB runs code
- lib/source-storybook.mjs 18 KB runs code
- lib/story-imports.mjs 15 KB runs code
- lib/sync-hashes.mjs 11 KB runs code
- non-storybook/SKILL.md 58 KB
- package-build.mjs 54 KB runs code
- package-capture.mjs 15 KB runs code
- package-validate.mjs 51 KB runs code
- resync.mjs 23 KB runs code
- storybook/compare.mjs 45 KB runs code
- storybook/http-serve.mjs 1.8 KB runs code
- storybook/probe.mjs 6.9 KB runs code
- storybook/SKILL.md 68 KB
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.
- 11d ago First seen · 128 lines · 56 tokens per session scan A 46763c9ea2f2
design-sync is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,614 stars, last pushed yesterday), licensed CC0-1.0. It adds 56 tokens to every session and 6,366 once invoked, about $0.0003 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).
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
impeccable
Frontend design guidance, upstream-maintained (impeccable).
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
ambience-skill
Layer A ambience-and-typographic-motion reference anchored to the react-bits catalog (reactbits.dev). Stacks on any style skill whenever work adds a hero atmosphere, an animated or shader background, a typographic reveal (split, blur, shimmer, typewriter, count-up, marquee), scroll storytelling, or card surface…