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 plugin-authoringgit 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/plugin-authoring)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/plugin-authoring"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/plugin-authoring/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/plugin-authoring"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/plugin-authoring.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 | $0.00083 | $0.01805 |
| Opus 5 | $0.00042 | $0.00903 |
| Sonnet 5 | $0.00017 | $0.00361 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
plugin-authoring scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are about to write, extend or debug a plugin made of function hooks. This note is orientation: what such a plugin is, where its exact contract is written down for the build you are running in, and where to look when something does not take. The API is early access and moves between releases, so treat the generated declarations as the authority and this note as the map to them.
What a plugin of function hooks is
A plugin is a folder with a .claude-plugin/plugin.json manifest. Its
function hooks live in one hooks module: a TypeScript or JavaScript file
that hooks/hooks.json names under modules (one path, relative to that
file), exporting register(on, options). on(event, matcher?, hook) adds a
hook; options holds the values of the fields the manifest's userConfig
declares. Every hook has the shape ($, e, next): $ is the engine
interface (display, model, session, prompt, tools, filesystem, store,
clock, network, host commands, settings, environment and the rest), e is the event's input as a plain value,
and next(e) continues to the other plugins and then the engine's own
behaviour, resolving to the event's result. A hook that returns without
calling next answers for itself; one that calls next({ ...e, ... })
rewrites what the rest of the chain sees, within what that event allows.
The module runs in an environment of its own, with no DOM and no Node:
everything outside it is reached through $. JSX is available with h as
the factory.
The events cover tool calls and their descriptions, the prompt as
submitted, the system prompt's sections and the first message's context
blocks, what the interface draws, the turn's start, steps and completion,
the session's start and its inbound deliveries, skills, subagents and
attribution text. Which of them a feature is, and what it needs from $,
are the two questions worth settling before writing anything.
The types are the reference
Do not guess at an event's input, a method on $, or an element's props.
Run /plugin-types in the session (it takes an optional directory and
defaults to .claude/types). It writes two files from the running build:
claude-code.d.ts, which declares the module claude-code (import types
from it; at run time the import is empty), the globals a hooks module has,
and the inputs of this build's built-in tools; and claude-code-mcp.d.ts,
the inputs of the MCP tools connected right now, so e narrows per tool.
The header of claude-code.d.ts carries a tsconfig.json that fits a hooks
module and shows how to type register against Register.
What ships with it
2 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.
- 2d ago First seen · 126 lines · 83 tokens per session scan A a4884b9cb174
plugin-authoring is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,893 stars, last pushed 2d ago), licensed CC0-1.0. It adds 83 tokens to every session and 1,805 once invoked, about $0.0004 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 2026-09-10.
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.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
pretext
Build creative browser demos with DOM-free text layout.
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.