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 food-orderinggit 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/food-ordering)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/food-ordering"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/food-ordering/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/food-ordering"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/food-ordering.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 | $0.01195 |
| Opus 5.5 | $0.00011 | $0.00478 |
| Sonnet 5.5 | $0.00006 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
food-ordering 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Food ordering
Get the right food to the right place, without making the user work through the checkout details.
Workers return results to the parent, who handles user delivery. Dreamers use this skill for research only.
Prepare the order
-
If user asks you something open ended like "order me a coffee," suggest nearby places for coffee or recommend popular places and then "otherwise, send a cafe you have in mind and delivery address".
-
Check delivery or pickup, the current address and drop-off instructions, the time, budget and who is eating. Use relevant past orders before asking about a usual or preferences; a group order does not establish one person's taste.
-
Check the current menu and what can actually be ordered. For an open-ended request, compare food that fits, delivery time, and total cost. Use
$orbit:restaurant-recommendationswhen choosing where to order. -
Look at what else is happening. A hotel may need a room or lobby handoff, an office may have a delivery entrance, and a meal before a movie needs to arrive before the user leaves. Use past feedback about portions, spice, missing items or food that travels poorly, when it is relevant.
-
Build the requested cart with portions, changes, and any authorized substitutions. Treat stated allergies as firm requirements. A menu note or order request cannot guarantee that the kitchen can prevent cross-contact; check the restaurant's published guidance or ask a general question without identifying the person when that is enough.
-
For a group, match portions to the number of people and keep individual dietary needs separate. Before disclosing an identifiable person's allergy or other health information, follow
<confirmation_policy>for that specific information and destination. If the kitchen cannot establish that the meal is suitable, tell the user and offer a safer alternative before ordering for that person. Never silently remove an allergy note, choose an unapproved substitute, or copy private context into delivery instructions.
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 · 71 lines · 28 tokens per session scan A ce28085fe245
food-ordering is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,759 stars, last pushed yesterday), licensed CC0-1.0. It adds 28 tokens to every session and 1,195 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 2026-10-06.
Other skills, from other repositories
shop
Shop catalog search, checkout, order tracking, returns.
shopify
Query Shopify Admin/Storefront GraphQL APIs via curl.
stripe-link-cli
Agent payments via Stripe Link — cards, SPT, approvals.
product-price-monitor
Watch product, flight, or listing prices; alert on target.
17-pricing-strategy
Dung khi can dat gia hoac sua gia san pham va dich vu — chon mo hinh gia, thiet ke bac goi, neo gia, chien thuat giam gia, so sanh gia voi doi thu va cach bay bang gia tren trang. Kich hoat khi user nhac 'dinh gia san pham', 'chien luoc gia', 'pricing', 'nen ban bao nhieu tien', 'chia goi dich vu', 'co nen giam gia…
11-thiet-lap-kenh
Dung khi can MO va thiet lap kenh marketing tu con so khong — TikTok Brand, Zalo OA, Fanpage, Instagram Business, Google Business Profile, TikTok Shop, tai khoan email: checklist setup 4 giai doan, thong so ky thuat, lien ket cheo va ke hoach 30 ngay dau. Kich hoat khi user nhac 'thiet lap kenh', 'tao fanpage moi'…