sheets

sheets is a skill for Claude Code, Codex from zackbart/connecta. It costs 2 tokens per session (757 once invoked), scanned A, original, MIT.

A skill for reading and editing the signed-in person's Google Sheets. Google Sheets is Google's online spreadsheet service, and access is limited to spreadsheets that person can open.

In plain words
What is it for?
Use it to inspect spreadsheet structure, read cell ranges, and work with spreadsheet data through Google Drive-found file IDs.
Why use it?
It helps find the correct spreadsheet and range, handle sheet names and paging, and avoid requesting data from an inaccessible or guessed location.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect spreadsheet structure, read cell ranges, and work with spreadsheet data through Google Drive-found file IDs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zackbart/connecta/sheets
Install

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.

Any agent
npx skills add zackbart/connecta --skill sheets
Clone the repo
git clone --depth 1 https://github.com/zackbart/connecta

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sheets

README.md
[![agentmods](https://agentmods.dev/badge/skills/zackbart/connecta/sheets/github.svg)](https://agentmods.dev/skills/zackbart/connecta/sheets)
Your own site
<a href="https://agentmods.dev/skills/zackbart/connecta/sheets"><img src="https://agentmods.dev/badge/skills/zackbart/connecta/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.

agentmods 80×15 button for sheets

Your own site · 80×15
<a href="https://agentmods.dev/skills/zackbart/connecta/sheets"><img src="https://agentmods.dev/badge/skills/zackbart/connecta/sheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00002 $0.00757
Opus 5.5 $0.00001 $0.00303
Sonnet 5.5 $0.00000 $0.00151
Haiku 4.5 $0.00000 $0.00076

Measured 6d ago against content hash c20f80088179, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (fixtures.ts, index.ts, provider.test.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/providers/sheets/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Sheets usage

Acts as the signed-in person in their own Google Sheets through Workspace delegation: it reaches only spreadsheets they can open, starting from an id.

Connection purpose:

Whose spreadsheets

Every call acts as the Workspace account deployment config maps the caller to. No argument names an account. A call with none mapped fails auth_required; only an operator can change the mapping. An id that is unknown or not shared with this person fails the same way — Google does not say which.

Finding a spreadsheet

  • Sheets cannot list or search files. Find one by name with a Google Drive search, or take the id from its URL (between /d/ and /edit).
  • get_spreadsheet first: sheet titles, ids, grid sizes, and named ranges, so ranges are named right rather than guessed.

Ranges

  • A1 notation. Quote a sheet title with spaces or punctuation: 'Q3 Budget'!A1:D20, doubling any ' inside it. A bare title is the whole sheet; Sheet1!B:B a whole column; a named range works by name.
  • get_values pages by whole rows under maxCells and maxBytes: page with page.nextCursor and the same spreadsheetId, ranges, and render options. A range with explicit rows (A1:D500, B:D) resumes where it stopped; a sheet title or named range is re-read and its earlier rows skipped, so rowOffset says how far into Google's echoed range the page starts.
  • A row too wide or too large for one page is refused, not cut: narrow the columns or lower maxCellChars. The default maxBytes is what execute_code can receive; raise it only for a direct call_tool read.
  • A cell over

characters ends with a truncation marker; read it alone with maxCellChars for the rest. Reduce inside execute_code before returning a large read.

Writing

  • valueInputOption is required: RAW stores text as given; USER_ENTERED parses it as typed, so a leading = makes a formula. Use RAW for data from outside the spreadsheet.
  • In written rows, null leaves a cell as it was and "" empties it.
  • append_values inserts rows below the table and overwrites nothing; update_values and batch_update_values overwrite the cells they cover; clear_values empties values but keeps formatting.
  • batch_update_spreadsheet takes Google's own Request objects for everything else (formatting, sorting, deleting rows or sheets); it is atomic, always needs approval, and can destroy data. Replies too large to return come back cut to their kind, ids, and counts with a note; the requests still applied, so never send them again to see the rest.
  • Sheets has no revision check on writes: edits are last-writer-wins, so a person editing the same cells meanwhile is overwritten without warning. Read just before writing over anything a person may be editing.
  • Moving, sharing, or deleting a spreadsheet file is Drive's job.

Read the full file on GitHub · 74 lines

Files

What ships with it

5 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.

Changes

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.

  1. 6d ago First seen · 74 lines · 2 tokens per session scan A c20f80088179

Subscribe to this mod's changes

sheets is a skill published in the GitHub repository zackbart/connecta (0 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 757 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 2026-10-08.