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 schedulegit 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/schedule)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/schedule"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/schedule/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/schedule"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/schedule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00024 | $0.02640 |
| Opus 5 | $0.00012 | $0.01320 |
| Sonnet 5 | $0.00005 | $0.00528 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade A, and why
schedule scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use the `RemoteTrigger` tool (load it first with `ToolSearch select:RemoteTrigger`; auth is handled in-process — do not use curl): How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schedule Cloud Agents
You are helping the user schedule, update, list, or run cloud Claude Code agents. These are NOT local cron jobs — each routine spawns a fully isolated cloud session (CCR) in Anthropic's cloud infrastructure, either on a recurring cron schedule or once at a specific time. The agent runs in a sandboxed environment with its own git checkout, tools, and optional MCP connections.
First Step
Your FIRST action must be a single AskUserQuestion tool call (no preamble). Use this EXACT string for the question field — do not paraphrase or shorten it:
"What would you like to do with scheduled cloud agents?"
Set header: "Action" and offer the four actions (create/list/update/run) as options. After the user picks, follow the matching workflow below.
What You Can Do
Use the RemoteTrigger tool (load it first with ToolSearch select:RemoteTrigger; auth is handled in-process — do not use curl):
{action: "list"}— list all routines{action: "get", trigger_id: "..."}— fetch one routine{action: "create", body: {...}}— create a routine{action: "update", trigger_id: "...", body: {...}}— partial update{action: "run", trigger_id: "..."}— run a routine now{action: "list_runs", trigger_id: "..."}— the routine's recent run sessions, most recently active first{action: "get_run_log", session_id: "..."}— condensed log of one run (provisioning, tool calls and errors, permission denials, API retries, final result)
To debug a routine that misbehaved, call list_runs and then get_run_log on the run in question. A fire that was skipped or refused before a session existed (routine paused, a fire cap, a kill switch) or that failed its pre-creation checks (repository access, environment) leaves no run in list_runs, and a routine that posts into an existing session adds to that session rather than a new run; when the list is empty or short, check the routine itself with get rather than concluding it never fired.
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.
- today Changed · +1 lines e0e19d78a345
- 11d ago First seen · 178 lines · 24 tokens per session scan A d03a126fcba4
schedule is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (64,614 stars, last pushed yesterday), licensed CC0-1.0. It adds 24 tokens to every session and 2,640 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.