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 withingsgit 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/withings)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/withings"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/withings/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/withings"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/withings.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 | $0.01487 |
| Opus 5.5 | $0.00011 | $0.00595 |
| Sonnet 5.5 | $0.00006 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
withings 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Withings
Query Withings body measurements, activity, sleep, and workout data via the bundled withings CLI.
When to Use
Activate when the user asks about their Withings data:
- Body metrics (weight, BMI, body fat, blood pressure, heart rate)
- Daily activity (steps, calories, distance, active duration)
- Sleep sessions (score, stages, duration, breathing rate)
- Workout sessions (run/walk/cycle/etc.)
Tooling
Three subcommands cover most needs:
| Subcommand | Purpose |
|---|---|
withings status |
Connection state ({ok, status, connect_url?, disconnect_url?, reason?}). |
withings list-fields --category <CAT> |
Field list for a category (snake_case, units in the name). |
withings query --category <CAT> --start-date <YYYY-MM-DD> [--end-date --interval --fields] |
Typed snake_case records. Returns a JSON array. |
Categories
daily-metrics— Daily rollup of Activity (steps/calories/distance/HR) + Measures (weight/BP/body composition). Supports--interval hourly|daily|weekly(defaults todaily). Aggregation rules: sum for counters (step_count,active_energy_burned_kcal,distance_walking_running_meters), avg forhr_average_bpm, max forhr_max_bpm, last-of-bucket for body measurements (weight/BP/body fat etc.).sleep— One row per sleep session (score, stages, duration, HR, breathing).workout— One row per workout session (translatedworkout_typename, duration, distance, calories, HR).
Use list-fields to discover available fields per category.
Output
JSON to stdout. Datetimes are local YYYY-MM-DD HH:MM:SS per record's timezone. Session rows include id (prefixed withings_<id>), start_datetime, end_datetime, timezone. daily-metrics buckets include date / hour / week_start + record_count instead of id.
Examples
# Recent workouts
withings query --category workout --start-date 2026-05-01
# Weight trend (last reading per day)
withings query --category daily-metrics --start-date 2026-04-01 --fields body_mass_kg
# Weekly step totals
withings query --category daily-metrics --start-date 2026-04-01 --interval weekly --fields step_count
What ships with it
3 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 · 100 lines · 28 tokens per session scan A 067a1189e892
withings is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,918 stars, last pushed today), licensed CC0-1.0. It adds 28 tokens to every session and 1,487 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.