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 boxgit 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/box)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/box"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/box/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/box"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/box.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 | $0.00028 | $0.01033 |
| Opus 5.5 | $0.00011 | $0.00413 |
| Sonnet 5.5 | $0.00006 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
box 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 25d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Box
Use /opt/hatch/bin/box-cli to access Box.
Connect
Run /opt/hatch/bin/box-cli status. If disconnected, run
/opt/hatch/bin/box-cli authorize-url and share the returned connect_url
as Connect Box. A fresh connection requests read-only access. Wait for
browser consent, then check status again.
Before an operation that may need broader Box access, run
/opt/hatch/bin/box-cli status --for-command <command-or-method>. For a hosted
MCP operation, pass its exact tool name instead of call-tool. When
scope_status is not_granted, copy the returned scope_add_url exactly and
post it on its own line as
[Additional Box access](<scope_add_url>) so the client renders the native
access button. Wait for consent, then retry the original operation. Never
construct an authorization URL or substitute a raw Box scope. The operation
also fails closed with the same method-bound link if its required scope is
absent. OAuth access does not replace Muse approval.
Use
Run list-tools for available MCP tools, their argument schemas, and Muse
permissions. Use those schemas and IDs returned by Box in call-tool.
get_file_content reads document text. Downloads and changes ask for Muse
approval by default.
/opt/hatch/bin/box-cli list-tools
/opt/hatch/bin/box-cli call-tool --name who_am_i --arguments-json '{}'
# Browse the root folder.
/opt/hatch/bin/box-cli call-tool --name list_folder_content_by_folder_id \
--arguments-json '{"folder_id":"0","limit":20}'
# Search for PDFs.
/opt/hatch/bin/box-cli call-tool --name search_files_keyword \
--arguments-json '{"query":"project plan","file_extensions":["pdf"],"limit":10}'
# Inspect file metadata.
/opt/hatch/bin/box-cli call-tool --name get_file_details \
--arguments-json '{"file_id":"<file_id>","fields":["name","size","permissions"]}'
# Read document text.
/opt/hatch/bin/box-cli call-tool --name get_file_content \
--arguments-json '{"file_id":"<file_id>"}'
# Create a folder.
/opt/hatch/bin/box-cli call-tool --name create_folder \
--arguments-json '{"name":"Project notes","parent_folder_id":"<folder_id>"}'
# Upload a text file.
/opt/hatch/bin/box-cli call-tool --name upload_file \
--arguments-json '{"file_name":"notes.txt","file_content":"Meeting notes","parent_folder_id":"<folder_id>"}'
# Post a comment.
/opt/hatch/bin/box-cli call-tool --name create_file_comment \
--arguments-json '{"file_id":"<file_id>","message":"Ready for review."}'
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.
- 25d ago First seen · 97 lines · 28 tokens per session scan A 2924b47d621a
box is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,425 stars, last pushed today), licensed CC0-1.0. It adds 28 tokens to every session and 1,033 once invoked, about $0.0001 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 2026-10-05.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
PDF files: create, read, merge, fill, OCR, edit text.
siyuan
Query and edit a SiYuan knowledge base via its API.