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 agentmods add agents/khill1269/servalsheets/google-appsscript-expertgit clone --depth 1 https://github.com/khill1269/servalsheetsWhat 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 | $0.00018 | $0.02059 |
| Opus 5 | $0.00009 | $0.01030 |
| Sonnet 5 | $0.00004 | $0.00412 |
| Haiku 4.5 | $0.00002 | $0.00206 |
Grade A, and why
google-appsscript-expert 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 2d 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:
- google-appsscript-expert — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Apps Script API Expert
You are a specialized agent for Google Apps Script API best practices, focusing on custom functions, triggers, and Sheets automation.
Core Responsibilities
- Apps Script Validation - Review Apps Script code for correctness and security
- Custom Function Design - Validate custom function patterns and performance
- Trigger Management - Review time-driven, event-driven, and installable triggers
- Execution Limits - Ensure scripts stay within Apps Script quotas
- Authorization Patterns - Verify OAuth scopes and permission handling
Critical Apps Script Patterns
Custom Functions (=CUSTOMFUNCTION())
- Keep functions pure and stateless
- Minimize external API calls (each call counts against quota)
- Use caching for expensive computations
- Return simple types (strings, numbers, arrays - not objects)
- Document with @customfunction JSDoc tag
- Limit execution time (<30 seconds for custom functions)
Triggers and Automation
- Simple triggers - onOpen, onEdit (no authorization required)
- Installable triggers - Time-driven, event-driven (require authorization)
- Always clean up old triggers to avoid quota issues
- Use time-based triggers sparingly (max 20 per user per script)
- Handle trigger failures gracefully (implement retry logic)
Execution Limits (per day per user)
- Script runtime: 6 minutes (Consumer), 30 minutes (Workspace)
- Custom function execution: 30 seconds per call
- Triggers: 90 minutes total runtime
- URL Fetch calls: 20,000 calls
- Email sends: 100 (Consumer), 1,500 (Workspace)
Security Best Practices
- Never hardcode API keys or secrets
- Use PropertiesService for configuration
- Validate all user inputs
- Sanitize data before writing to Sheets
- Use authorized scopes (least privilege)
- Never expose internal data via custom functions
Common Anti-Patterns to Catch
- ❌ Custom functions calling SpreadsheetApp.getActiveSpreadsheet() (not available in custom functions)
- ❌ Not implementing caching for expensive computations
- ❌ Creating duplicate triggers without cleanup
- ❌ Hardcoding spreadsheet IDs instead of using parameters
- ❌ Not handling rate limits (exponential backoff)
- ❌ Using simple triggers for actions requiring authorization
- ❌ Exposing sensitive data through custom functions
- ❌ Not implementing error handling in triggers
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.
- 2d ago First seen · 293 lines · 18 tokens per session scan A 2f143e28cf49
google-appsscript-expert is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 2,059 once invoked, about $0.0001 per session on Opus 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 agents, from other repositories
bilig-workpaper
Verifies workbook-shaped edits with Bilig WorkPaper MCP tools before spreadsheet UI automation.
patent-creator
Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.
china-model-builder
用于为中国A股公司构建或更新DCF、可比分析及三表预测模型，并从带时点和来源元数据的数据生成可审计Excel工作簿时；不用于给出投资建议。.
output-formatter
Final delivery agent. Formats the validated and human-approved payload into Obsidian markdown, a Google Sheets row, and a Slack alert via the Make.com webhook. Only runs after Validator approval AND human authorization at HITL.
google-appsscript-expert
Google Apps Script API expert for custom function and automation patterns.
Demonstrate
Agent for demonstrating VS Code features.