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 OpenKnots/okcode --skill spreadsheetgit clone --depth 1 https://github.com/OpenKnots/okcodeWrote 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/openknots/okcode/spreadsheet)<a href="https://agentmods.dev/skills/openknots/okcode/spreadsheet"><img src="https://agentmods.dev/badge/skills/openknots/okcode/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/openknots/okcode/spreadsheet"><img src="https://agentmods.dev/badge/skills/openknots/okcode/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 | $0.00011 | $0.00441 |
| Opus 5.5 | $0.00004 | $0.00176 |
| Sonnet 5.5 | $0.00002 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
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 1mo 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.
What it actually says
Spreadsheet Skill
When to use this skill
- Use when the task involves spreadsheets, CSV/TSV files, tabular data cleanup, or workbook analysis.
- Use when the user needs formulas, summaries, transformations, or structured exports from spreadsheet data.
- Use when the task depends on preserving headers, column types, sheet boundaries, or formulas.
- Use when bulk edits must remain auditable and reversible.
What this skill does
- Normalizes spreadsheet-like tasks into safe, repeatable tabular workflows.
- Treats headers, row counts, formulas, and delimiters as explicit assumptions rather than guessing silently.
- Prefers scripted transformations that can be reviewed and rerun.
- Helps separate data cleaning, calculation, and presentation concerns.
Implementation
- First identify the source format: CSV, TSV, XLSX, multiple sheets, exported report, or ad hoc table.
- Confirm the shape of the data before editing: headers, unique keys, empty rows, encoding, delimiters, and date formats.
- If formulas are involved, clarify whether they should be preserved, recalculated, or replaced with values.
- For bulk updates, favor scriptable transforms that produce a clear before/after story.
- Preserve source data before rewrites, especially when changing delimiters, formulas, or workbook structure.
- If workbook layout matters, call out any gap between plain-text data processing and full spreadsheet fidelity.
- Summarize row-level and column-level impacts after non-trivial edits.
Best practices
- Never assume the first row is a header without checking.
- Treat date, currency, and numeric coercion as high-risk transformations.
- Preserve formulas unless the user explicitly wants static values.
- Prefer small, auditable transformations over opaque bulk rewrites.
- State when workbook-only features such as formatting, filters, merged cells, or charts may not be preserved.
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.
- 1mo ago First seen · 50 lines · 11 tokens per session scan A 015e5cbbe029
spreadsheet is a skill published in the GitHub repository OpenKnots/okcode (24 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 441 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
gsheets
Google Sheets via MCP — read, write, create, list, share spreadsheets. Use when reading, writing, or managing Google Sheets data.
CSV / Spreadsheet Operations
List sheets, read rows, read a single line, and write back to spreadsheets. Supports .csv / .tsv / xlsx / Google Sheets. Canonical partner for agentbatch when iterating row-by-row.
data-analysis
Analyze spreadsheet data, generate insights, create visualizations, and build reports from Excel/CSV data.
xlsx-engineer
You are the XLSX Engineering Specialist. You create, edit, analyze, and validate Excel spreadsheet files with professional formatting, working formulas, and zero errors.
csv-processor
A tool for working with CSV files, which are plain-text tables whose values are separated by commas or similar delimiters.