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 stripegit 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/stripe)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/stripe"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/stripe/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/stripe"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/stripe.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 | $0.00062 | $0.00461 |
| Opus 5.5 | $0.00025 | $0.00184 |
| Sonnet 5.5 | $0.00012 | $0.00092 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
stripe 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.
What it actually says
Stripe
Use the installed stripe CLI. Start with stripe status. If it reports
not_connected, run stripe authorize-url and share only the returned
connect_url with the user.
OAuth uses Dynamic Client Registration and PKCE through authd. Stripe issues a per-VM public client, so no shared credential enters Muse and credentials must never be requested in chat.
Run stripe list-tools to inspect the live provider catalogue and schemas,
then call an advertised tool with:
stripe call-tool --name <tool> --arguments-json '<json-object>'
The OAuth connection identifies the merchant account. Never ask the user for
that connected account's acct_... ID. If another tool requires
stripe_context, first call the advertised list_available_accounts_or_orgs
tool with an empty arguments object and use a context it returns. If more than
one context matches the requested live or test mode, present their names and
ask the user which account to use; do not ask them to paste an account ID. Never
invent a context or call an account-scoped tool without one returned by Stripe.
list-tools exposes only reviewed Stripe tools and includes each tool's
hatch_permission, hatch_action, and hatch_permission_label. Unknown or
new provider tools remain unavailable until reviewed. For stripe_api_write,
the returned schema lists the reviewed stripe_api_operation_id values and
their operation-specific permission overrides; unlisted operation IDs are not
available. Read permissions follow the user's connector settings; Stripe API
writes and feedback require granular approval. Stripe may also require
confirmation through a provider URL for sensitive operations. Do not retry a
failed or timed-out write automatically because its side effect may have
completed.
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.
- 11d ago First seen · 47 lines · 62 tokens per session scan A 5e4473e367ef
stripe is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,707 stars, last pushed 2d ago), licensed CC0-1.0. It adds 62 tokens to every session and 461 once invoked, about $0.0002 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
stripe-link-cli
Agent payments via Stripe Link — cards, SPT, approvals.
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.
shopify
Query Shopify Admin/Storefront GraphQL APIs via curl.
evm
Read-only EVM client: wallets, tokens, gas across 8 chains.