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 artifact-template-analytics-dashboardgit 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/artifact-template-analytics-dashboard)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/artifact-template-analytics-dashboard"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/artifact-template-analytics-dashboard/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/artifact-template-analytics-dashboard"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/artifact-template-analytics-dashboard.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 | $0.00047 | $0.00274 |
| Opus 5.5 | $0.00019 | $0.00110 |
| Sonnet 5.5 | $0.00009 | $0.00055 |
| Haiku 4.5 | $0.00005 | $0.00027 |
Grade A, and why
artifact-template-analytics-dashboard 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 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.
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.
Copies of this mod
6 near-identical copies found in the catalogue:
- artifact-template-operating-calendar — 89% identical, 6 lines differ
- artifact-template-strategy-memorandum — 84% identical, 14 lines differ
- artifact-template-design-report — 80% identical, 14 lines differ
- artifact-template-experiment-analysis — 78% identical, 14 lines differ
- artifact-template-investment-committee-memo — 77% identical, 14 lines differ
- artifact-template-legal-memorandum — 77% identical, 14 lines differ
What it actually says
Analytics Dashboard
Create a new spreadsheet from this template. Keep the reference file unchanged.
Workflow
- Read
artifact-template.jsonand resolve its paths relative to this skill directory. - Identify the prompt-advertised preinstalled spreadsheet capability. Use the available resource or filesystem tool to open its advertised resource, plugin, skill, or file target, then follow its reference/template workflow with the retained file. If no such capability can be identified and read, say it is unavailable and stop; do not recreate or install it.
- Treat the user's prompt and available sources as the content input. Do not invent facts merely to fill a template slot.
- Clone or import the reference instead of replacing its visual system with generic defaults.
- Render and verify the finished spreadsheet, then return the final artifact.
Fidelity
Preserve sheet structure, formulas, names, number formats, dimensions, tables, charts, validation, conditional formatting, and frozen panes.
User instructions control requested content and explicit deviations. The retained reference controls layout and formatting where the user has not requested a change.
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 First seen · 23 lines · 47 tokens per session scan A cf5360fd8b19
artifact-template-analytics-dashboard is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,966 stars, last pushed today), licensed CC0-1.0. It adds 47 tokens to every session and 274 once invoked, about $0.0002 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 2026-11-07.
artifact-template-analytics-dashboard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| artifact-template-analytics-dashboardasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 47 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |
| comps-analysisNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 13 | Claude Code, Codex |
| lbo-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 19 | Claude Code, Codex |
| google-workspaceNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 21 | Claude Code, Codex |
| 3-statement-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 18 | Claude Code, Codex |
| merger-modelNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 18 | Claude Code, Codex |