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 handoff-to-claude-codegit 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/handoff-to-claude-code)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/handoff-to-claude-code"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/handoff-to-claude-code/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/handoff-to-claude-code"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/handoff-to-claude-code.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 | $0.00012 | $0.00882 |
| Opus 5 | $0.00006 | $0.00441 |
| Sonnet 5 | $0.00002 | $0.00176 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
handoff-to-claude-code 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:
- handoff-to-claude-code — 94% identical, 9 lines differ
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff to Claude Code
Create a comprehensive handoff package so a developer using Claude Code can implement this design in a real codebase.
Steps
-
Create a handoff folder in the project directory:
mkdir -p <project-folder>/design_handoff_<feature-name>/Use a descriptive feature name derived from the design (e.g.,
design_handoff_onboarding_flow,design_handoff_settings_redesign). -
Create a README.md in the handoff folder with the following sections:
README.md Structure
# Handoff: <Feature Name>
## Overview
Brief description of what this design is for and what it accomplishes.
## About the Design Files
State clearly that the files in this bundle are **design references created in HTML** — prototypes showing intended look and behavior, not production code to copy directly. Explain that the task is to **recreate these HTML designs in the target codebase's existing environment** (React, Vue, SwiftUI, native, etc.) using its established patterns and libraries — or, if no environment exists yet, to choose the most appropriate framework for the project and implement the designs there.
## Fidelity
State clearly whether the mocks/prototypes created in this conversation are:
- **High-fidelity (hifi)**: Pixel-perfect mockups with final colors, typography, spacing, and interactions. The developer should recreate the UI pixel-perfectly using the codebase's existing libraries and patterns.
- **Low-fidelity (lofi)**: Wireframes or rough layouts showing structure and flow. The developer should use these as a guide for layout and functionality but apply the codebase's existing design system for styling.
## Screens / Views
For each screen or view in the design:
- **Name**: What this screen is called
- **Purpose**: What the user does here
- **Layout**: Detailed description of the layout (grid structure, flex directions, widths, heights, margins, padding)
- **Components**: List each UI component with:
- Position and size
- Colors (exact hex values if hifi)
- Typography (font family, size, weight, line-height, letter-spacing)
- Border radius, shadows, borders
- Hover/active/focus states
- Content/copy (exact text used)
## Interactions & Behavior
- Click handlers and navigation flows
- Animations and transitions (duration, easing, properties)
- Hover states
- Loading states
- Error states
- Form validation rules
- Responsive behavior (if applicable)
## State Management
- What state variables are needed
- State transitions and their triggers
- Any data fetching requirements
## Design Tokens
List all design values used:
- Colors (with hex values)
- Spacing scale
- Typography scale
- Border radius values
- Shadow values
## Assets
List any images, icons, or other assets used in the design and where they came from.
## Files
List the HTML/CSS/JS files in the project that contain the design, so the developer can reference them.
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 · 90 lines · 12 tokens per session scan A 96032b8aab2b
handoff-to-claude-code is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,614 stars, last pushed yesterday), licensed CC0-1.0. It adds 12 tokens to every session and 882 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
comps-analysis
Build comparable-company valuation workbooks in Excel.
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.
honcho
Configure and troubleshoot Honcho memory for Hermes.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
pretext
Build creative browser demos with DOM-free text layout.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.