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 loopgit 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/loop)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/loop"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/loop.svg" alt="Measured on agentmods" height="20"></a>- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01777 |
| Opus 5 | $0.00018 | $0.00889 |
| Sonnet 5 | $0.00007 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
loop 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 8d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loop — autonomous default with dynamic pacing
The user invoked /loop with no prompt and no interval. Run the autonomous check now, then self-pace the next iteration via ScheduleWakeup — no cron.
Action
- Run the autonomous check now, following the instructions inlined below.
- If the next tick is gated on an event (CI finishing, a PR comment, a log line) and no Monitor is already running for it: arm one now with
persistent: true. Its events wake this loop immediately — you do not wait for the ScheduleWakeup deadline. Arm once; on later ticks call TaskList first and skip if a monitor is already running. - Briefly confirm: that this is the autonomous default in dynamic-pacing mode, that you ran the check now, whether a Monitor is the primary wake signal, and what fallback delay you're about to pick. Write this as text before calling ScheduleWakeup — the turn ends as soon as that tool returns.
- Then, as the last action of this turn, decide whether the loop continues. If the next check is worth running, call ScheduleWakeup with:
delaySeconds: with a Monitor armed this is the fallback heartbeat (lean 1200–1800s). Without one, pick based on what you observed this turn — quiet branch? wait longer. Lots in flight? wait shorter. Read the tool's own description for cache-aware delay guidance.reason: one short sentence on why you picked that delay.prompt: the literal string<<autonomous-loop-dynamic>>— the dynamic-mode sentinel expands at fire time to the full instructions (first fire / first fire post-compact / loop.md edited) or a dynamic-pacing-specific short reminder (subsequent fires). Do not pass the full instructions; that is handled automatically.noop:trueif this tick changed nothing ("still waiting", "quiet hold");falseif it did something worth keeping. Consecutivenoop: trueticks collapse in the terminal. If it isn't, stop instead (step 6) — re-arming is a per-turn choice, not a default.
- If woken by a
<task-notification>rather than this prompt: handle the event, then make the same decision. If the loop should continue, call ScheduleWakeup again with<<autonomous-loop-dynamic>>and the same 1200–1800sdelaySeconds(the Monitor remains the wake signal; the new wakeup is only the fallback heartbeat). If the event means the work is finished, stop (step 6). - To stop the loop — the task is complete, further iterations can't make progress, or the user asked you to stop — call ScheduleWakeup with
stop: true(no other fields) and TaskStop any Monitor you armed (use TaskList to find the task ID if it is no longer in context). Stopping is the loop's normal ending — the user can restart it anytime with /loop. Before you stop, send a one-line outcome via PushNotification — the user may be away and waiting to hear it's done. Skip this if you're stopping because the user just told you to; they're already here.
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.
- 8d ago First seen · 51 lines · 36 tokens per session scan A a278f6ea693b
loop is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,387 stars, last pushed today), licensed CC0-1.0. It adds 36 tokens to every session and 1,777 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
honcho
Configure and troubleshoot Honcho memory for Hermes.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
pretext
Build creative browser demos with DOM-free text layout.