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 spreadsheetgit 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/spreadsheet)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/spreadsheet"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/spreadsheet/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/spreadsheet"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/spreadsheet.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 | $0.00113 | $0.00834 |
| Opus 5.5 | $0.00045 | $0.00334 |
| Sonnet 5.5 | $0.00023 | $0.00167 |
| Haiku 4.5 | $0.00011 | $0.00083 |
Grade A, and why
artifact_spreadsheet 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spreadsheet artifacts
An xlsx is generated with the preinstalled openpyxl library from a
generator script. Keep the generator under .src/: it is the editable
source for future revisions, and the binary is always regenerated from it.
| Task | Path |
|---|---|
| Create, or edit with formulas and formatting | openpyxl |
| Quick look at an existing sheet | muse.read (converted to markdown, paged); it carries no cell coordinates, so never plan edits from it |
| Read a workbook's model (formulas AND their values) | two load_workbook passes; see /opt/hatch/skills/artifacts/spreadsheet/references/formulas.md |
| Bulk or messy tabular data in or out | Python csv from the standard library; pip install --break-system-packages pandas when a task genuinely needs it |
| Design, structure, number formats, model conventions | /opt/hatch/skills/artifacts/spreadsheet/references/visual.md |
| Formulas, recalculation, editing existing workbooks | /opt/hatch/skills/artifacts/spreadsheet/references/formulas.md |
Requirements on every delivered workbook:
- Set a non-empty
workbook.properties.titleand a human-readable filename. Data enters the workbook from the build's gathered content only; a value you do not have is a blank cell or a question, never an invented number. - Write formulas, never precomputed results:
sheet["B10"] = "=SUM(B2:B9)", not the Python-computed total. The sheet must recalculate when its inputs change. - Follow the user's spec literally: their exact tab names, exact column headers, and the formula they spelled out. A redesign that computes something else fails, however elegant.
- Zero formula errors at delivery: run the recalculation gate below and fix what it names.
- Document assumptions and hardcoded numbers where the reader will see them (a cell comment or an adjacent labeled cell), citing the real source when one exists and saying plainly when the number came from the user.
- A workbook created for someone to fill in gets a short legend naming the cells to edit and one example row of realistic values; never add an example row to a file you were asked to edit.
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.
- 11d ago First seen · 57 lines · 113 tokens per session scan A 0f782a0fec9a
artifact_spreadsheet is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,707 stars, last pushed 2d ago), licensed CC0-1.0. It adds 113 tokens to every session and 834 once invoked, about $0.0005 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
xlsx
Create, read, edit Excel .xlsx workbooks and CSVs.
excel-author
Build auditable financial workbooks headless via openpyxl.