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 google-sheetsgit 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/google-sheets)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/google-sheets"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/google-sheets/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/google-sheets"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/google-sheets.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 | $0.00015 | $0.01283 |
| Opus 5.5 | $0.00006 | $0.00513 |
| Sonnet 5.5 | $0.00003 | $0.00257 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
google_sheets 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Sheets
Purpose
Manage Google Sheets through hatch_gws_cli; the vendored Google Workspace CLI is the only implementation path.
Tooling
Use exec to run:
hatch_gws_cli sheets <resource> <method> [flags]
Connection management
hatch_gws_cli sheets status
hatch_gws_cli sheets disconnect
Sheets operations
Core patterns:
hatch_gws_cli sheets statushatch_gws_cli sheets disconnecthatch_gws_cli schema sheets.spreadsheets.gethatch_gws_cli schema sheets.spreadsheets.createhatch_gws_cli schema sheets.spreadsheets.values.gethatch_gws_cli schema sheets.spreadsheets.values.appendhatch_gws_cli schema sheets.spreadsheets.batchUpdate
Common raw API calls:
hatch_gws_cli sheets spreadsheets get --params '{"spreadsheetId":"<spreadsheet_id>"}'hatch_gws_cli sheets spreadsheets create --json '{"properties":{"title":"My Spreadsheet"}}'hatch_gws_cli sheets spreadsheets values get --params '{"spreadsheetId":"<spreadsheet_id>","range":"Sheet1!A1:D10"}'hatch_gws_cli sheets spreadsheets values append --params '{"spreadsheetId":"<spreadsheet_id>","range":"Sheet1!A:D","valueInputOption":"USER_ENTERED"}' --json '{"values":[["a","b"],["c","d"]]}'hatch_gws_cli sheets spreadsheets batchUpdate --params '{"spreadsheetId":"<spreadsheet_id>"}' --json '{"requests":[{"addSheet":{"properties":{"title":"Q2"}}}]}'
Vendored helpers are also available:
hatch_gws_cli sheets +read ...hatch_gws_cli sheets +append ...
JSON output contract:
status: parsestatus,connect_url, anddisconnect_urldisconnect: parseok,action,status, anddisconnect_url
Formatting spreadsheet content
Write and format the spreadsheet through the Sheets API. Do not upload a file over it.
- Write the values with
spreadsheets.create,values.update, orvalues.append. SetvalueInputOptiontoUSER_ENTEREDso Sheets parses dates, currency, and formulas. - Set the styling in one
spreadsheets.batchUpdatecall.repeatCellwithuserEnteredFormatsets the header style and the number formats.updateSheetPropertiesfreezes the header row.updateDimensionPropertiessets column widths. A new spreadsheet can carry these formats in thespreadsheets.createbody instead. - Read the result back before you call it ready. A successful write proves the API accepted the request, not that the sheet reads correctly.
spreadsheets.getreturns no cell data by default, so pass a field mask:hatch_gws_cli sheets spreadsheets get --params '{"spreadsheetId":"<spreadsheet_id>","ranges":"<tab>!A1:F10","fields":"sheets(properties(title,gridProperties(frozenRowCount)),data(rowData(values(formattedValue,effectiveFormat(backgroundColor,numberFormat,textFormat)))))"}' - Never publish a
.xlsxfile over a spreadsheet withdrive files update. Google replaces the full contents of the file, so that upload discards every other tab and every edit the user made. To change one part of a spreadsheet, usevalues.updateorspreadsheets.batchUpdate. To give the user a workbook to download, build a spreadsheet artifact and attach the file.
What ships with it
1 file 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 · 79 lines · 15 tokens per session scan A e5808831c78d
google_sheets 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 15 tokens to every session and 1,283 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
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.