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 tessiegit 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/tessie)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/tessie"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/tessie/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/tessie"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/tessie.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 | $0.00020 | $0.00723 |
| Opus 5.5 | $0.00008 | $0.00289 |
| Sonnet 5.5 | $0.00004 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
tessie 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 15d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tessie (Tesla Vehicle Control)
Purpose
Use tessie-api to list vehicles, inspect status/state, and run explicit Tessie vehicle commands.
Tooling
Use:
tessie-api <subcommand> [options]
Core subcommands:
authorize-urlset-token --token '<TOKEN>'disconnectverifyvehiclesstatus --vin '<VIN>'state --vin '<VIN>'command --vin '<VIN>' --command <command_name> [--wait-for-completion] [--extra-query k=v]request --method GET --path '/<VIN>/battery' [--query k=v] [--json-body '{"...":"..."}']
JSON output contract:
authorize-url: parseok,authorize_url, andconnect_urlset-token: parseokandactiondisconnect: parseok,action,path, andremovedverify: parseok,action, anderror- all read/command calls: parse top-level
ok,status, andbody - common
bodyfields includeresults[],battery_level,battery_range,status, andresult
Auth
Manage Tessie auth through the CLI helpers only.
Auth contract:
- Run
tessie-api verifybefore Tessie API use when connection state is unknown. - If no API key is configured, run
tessie-api authorize-url. Whenconnect_urlis present, replace<connect_url>with the returned URL and share exactly this Markdown link:[Connect Tessie](<connect_url>); do not paste the raw URL separately. - The user can generate a token at
https://dash.tessie.com/settings/api. - If the user provides a key through the CLI flow, store it only through
tessie-api set-token --token '<TESSIE_API_TOKEN>'; do not write auth files directly. - Remove stored auth only through
tessie-api disconnect. - Never print token values.
Operating Rules
- If VIN is not given, call
vehiclesand ask user to pick one when multiple exist. - Use
statusorstatebefore impactful commands when the current vehicle condition matters. honk,flash,remote_boombox, software-update scheduling or cancellation, and fleet telemetry configuration may proceed from a clear, unambiguous request without an additional confirmation. Other vehicle commands and raw API writes use the connector approval gate; invoke the resolved command directly and do not add a duplicate chat confirmation. Never invent a command or infer a physical action the user did not request.- Use
command --command <name>only for explicit Tessie command names. Do not invent a mandatory pre-wake flow or undocumented helper behavior. - On HTTP or API errors, report
statusandbodyclearly. Common cases are401,408, and503. - Never print token values.
- Read results preserve Tessie's raw timestamps and add semantic UTC and user-local forms for state observations, last-seen values, and record creation/update times.
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.
- 15d ago First seen · 60 lines · 20 tokens per session scan A b13463976880
tessie is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,918 stars, last pushed today), licensed CC0-1.0. It adds 20 tokens to every session and 723 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
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
findmy
Track Apple devices/AirTags via FindMy.app on macOS.
openhue
Control Philips Hue lights, scenes, rooms via OpenHue CLI.
actual-setup
Set up Actual Computer (actual.inc) inference in Hermes.
openhue
Control Philips Hue lights and scenes via the OpenHue CLI.
camsnap
Capture frames or clips from RTSP/ONVIF cameras.