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 khill1269/servalsheets --skill guidesgit clone --depth 1 https://github.com/khill1269/servalsheetsWrote 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/khill1269/servalsheets/guides)<a href="https://agentmods.dev/skills/khill1269/servalsheets/guides"><img src="https://agentmods.dev/badge/skills/khill1269/servalsheets/guides/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/khill1269/servalsheets/guides"><img src="https://agentmods.dev/badge/skills/khill1269/servalsheets/guides.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 | $0.00018 | $0.04328 |
| Opus 5.5 | $0.00007 | $0.01731 |
| Sonnet 5.5 | $0.00004 | $0.00866 |
| Haiku 4.5 | $0.00002 | $0.00433 |
Grade A, and why
guides 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- guides — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ServalSheets Skill Guide for Claude
This guide helps Claude (and other AI assistants) use ServalSheets MCP server effectively.
Overview
ServalSheets provides 25 tools with 410 actions for comprehensive Google Sheets operations. It's production-grade with safety rails, semantic range resolution, and intelligent batching.
MCP Protocol Notes (2025-11-25)
ServalSheets follows MCP 2025-11-25. Use protocol-level features when available.
- Tool results are MCP CallToolResult. Prefer
structuredContent.response; checkresponse.successand readresponse.errorwhen false.isErrormay be set. - Tool inputs are wrapped under
request(e.g.,{ request: { action: 'read', ... } }). - Tool annotations are provided (readOnlyHint, destructiveHint, idempotentHint, openWorldHint). Use them to choose safe operations and confirm destructive changes.
- Resources:
sheets:///{spreadsheetId}returns spreadsheet metadata (properties + sheet list).sheets:///{spreadsheetId}/{range}returns range values (A1 notation; URL-encoded).knowledge:///formulas/financial.json,knowledge:///formulas/lookup.json,knowledge:///formulas/key-formulas.jsonknowledge:///templates/common-templates.jsonUse resources/list and resources/read to discover and load.
- Prompts: use
prompts/listto discover the full current set. Common starter workflows includewelcome,test_connection,first_operation,analyze_spreadsheet,transform_data,create_report, andclean_data. - Long operations may emit MCP progress notifications. Treat them as status only.
- Large reads may return
truncated: trueandresourceUri. You can read the URI with the range resource; if you cannot fetch it, request a narrower range or use batch reads.
Core Capabilities
1. Data Operations (sheets_data)
What it does: Read, write, append, and batch operations on cell values
Best practices:
- Use
valueRenderOption: 'FORMATTED_VALUE'for human-readable data - Use
valueRenderOption: 'UNFORMATTED_VALUE'for calculations - Always specify
valueInputOptionwhen writing (typically 'USER_ENTERED' for formulas) - Use batch operations for multiple ranges to save API calls
What ships with it
43 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.
- ACTION_REFERENCE.md 8.9 KB
- ADAPTIVE_BATCH_WINDOW_GUIDE.md 7.3 KB
- ADDING_A_HANDLER.md 21 KB
- ADDING_AN_ACTION.md 16 KB
- batching-strategies.md 12 KB
- caching-patterns.md 13 KB
- CLAUDE_ANALYSIS_WORKFLOW.md 23 KB
- CLAUDE_DESKTOP_OAUTH_SETUP.md 2.4 KB
- CLAUDE_DESKTOP_SETUP.md 25 KB
- CONFIRMATION_GUIDE.md 7.6 KB
- DEBUGGING.md 10 KB
- DEPLOYMENT.md 26 KB
- ERROR_HANDLING.md 12 KB
- ERROR_RECOVERY.md 25 KB
- FEATURE_FLAGS.md 30 KB
- FIREWALL_CONFIGURATION.md 3.8 KB
- FIRST_TIME_USER.md 5.0 KB
- GRAPHQL_API.md 984 B
- INSTALLATION_GUIDE.md 11 KB
- MCP_INSPECTOR_TESTING_GUIDE.md 8.8 KB
- MONITORING.md 46 KB
- OAUTH_INCREMENTAL_CONSENT.md 9.8 KB
- OAUTH_STANDARDIZED_SETUP.md 3.6 KB
- OAUTH_USER_SETUP.md 4.3 KB
- ONBOARDING.md 17 KB
- PERFORMANCE.md 39 KB
- PHASE_3_USER_GUIDE.md 20 KB
- PROMPTS_GUIDE.md 8.4 KB
- QUICKSTART_CREDENTIALS.md 5.8 KB
- quota-optimization.md 11 KB
- README.md 2.0 KB
- REMOTE_CONNECTOR_SETUP.md 6.0 KB
- SCHEMA_VERSIONING.md 11 KB
- sheets_appsscript.md 29 KB
- sheets_bigquery.md 34 KB
- sheets_dependencies.md 22 KB
- sheets_webhook.md 26 KB
- SMART_CHIPS.md 19 KB
- SUBMISSION_CHECKLIST.md 3.9 KB
- TABLE_MANAGEMENT.md 19 KB
- TEST_ACCOUNT_SETUP.md 7.0 KB
- TROUBLESHOOTING.md 22 KB
- USAGE_GUIDE.md 26 KB
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 · 595 lines · 18 tokens per session scan A b8dc74035178
guides is a skill published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 4,328 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 2026-08-31.
Other skills, from other repositories
gsheets
Google Sheets via MCP — read, write, create, list, share spreadsheets. Use when reading, writing, or managing Google Sheets data.
xlsx-edit
Edit or generate xlsx workbooks using either deterministic V1 office tools or a Python workbook script when higher fidelity is needed.
guides
This guide helps Claude (and other AI assistants) use ServalSheets MCP server effectively.
genoffice
Create, convert, read and edit Office documents locally with GenOffice's command line. Build a new presentation (pptx) from a brief through a checked outline, per-page spec and render pipeline, a new spreadsheet (xlsx) from CSV or JSON data with formulas, a new Word document (docx) from Markdown or HTML, or a PDF…
budget-planner
Turn a business plan into an annual or project budget with account lines, monthly spread, summaries and a separate assumptions sheet, delivered as an Excel workbook.
expense-report
Turn a pile of receipts into an expense claim summary that flags missing receipts, over-limit items and duplicates, delivered as an Excel workbook.