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 calendlygit 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/calendly)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/calendly"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/calendly/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/calendly"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/calendly.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 | $0.00022 | $0.00668 |
| Opus 5.5 | $0.00009 | $0.00267 |
| Sonnet 5.5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
calendly 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 18d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calendly
Purpose
Use the calendly CLI for Calendly connector status and scheduling-data reads.
Tooling
Use the installed CLI directly from PATH.
Core commands:
calendly statuscalendly disconnectcalendly authorize-urlcalendly mecalendly list-events --user-uri <uri> [--status active] [--min-start-time <iso>] [--max-start-time <iso>] [--count 20] [--page-token <token>]calendly event-types --user-uri <uri> [--active true] [--count 20] [--page-token <token>]calendly request --method GET --path '/scheduled_events' --query 'user=<uri>' [--query 'status=active'] [--json-body '<json>']
Output contract:
- Every command returns JSON with a top-level
ok. - For
disconnect, parseactionandremoved. - For
status, parse the reported connection state and any returned auth URL or recovery details. - For
me, parse the current user URI and organization URI before listing user-scoped resources. - For
list-eventsandevent-types, parse the returned collection plus any pagination token for follow-up pages. Timed scheduled events addevent_starts_at/event_ends_atwith UTC and user-local forms, and read outputs add runtime-generatedretrieved_at.
Auth
calendly owns the Calendly connection workflow.
Auth contract:
- Run
calendly statusfirst. - If the user wants to disconnect, run
calendly disconnect. - If not connected, run
calendly authorize-url. Whenconnect_urlis present, replace<connect_url>with the returned URL and share exactly this Markdown link:[Connect Calendly](<connect_url>); do not paste the raw URL separately. - After auth, run
calendly meto verify.
Credential storage:
- Client application credentials and user token state are never read directly by this skill.
- The CLI accesses connection state exclusively through shared
hatch-tool-sdkconnector helpers; there is no agent-visible config file path. - The CLI resolves and refreshes service tokens automatically; never print access or refresh tokens.
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.
- 18d ago First seen · 52 lines · 22 tokens per session scan A f34e375196db
calendly is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,052 stars, last pushed 3d ago), licensed CC0-1.0. It adds 22 tokens to every session and 668 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
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
subagent-dag-orchestration
Use when delegated work breaks into several tasks that agents on the roster can carry out. The host's role decides what to delegate; this skill decides how to group that work. A DAG node dispatches to a roster agent, including the generic agent, and cannot call the host's tools. Choose from the tool's subagent…
service-sop
A standard operating procedure for online domestic package-tour enquiries, from collecting trip needs through quoting, availability checks, presentation delivery, and follow-up. It also covers complaints, unusual requests, and group enquiries.