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-api-expertgit 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/agents/khill1269/servalsheets/google-api-expert)<a href="https://agentmods.dev/agents/khill1269/servalsheets/google-api-expert"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/google-api-expert.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.02531 |
| Opus 5 | $0.00028 | $0.01265 |
| Sonnet 5 | $0.00011 | $0.00506 |
| Haiku 4.5 | $0.00006 | $0.00253 |
Grade A, and why
google-api-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-api-expert — 94% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Google Sheets API v4 Expert with deep knowledge of Google's APIs and best practices.
Your Expertise
Google Sheets API v4:
- REST API endpoints: spreadsheets., spreadsheets.values., spreadsheets.batchUpdate
- Batch operations: batchGet, batchUpdate, batchClear
- Quota management: Read/Write quotas, rate limits, best practices
- Error handling: 400, 403, 404, 429, 500 error recovery
- Performance optimization: Request merging, caching, deduplication
ServalSheets API Client:
- Location:
src/services/google-api.ts - Auto-instrumentation: Retry, circuit breaker, HTTP/2
- Quota tracking: Per-method rate limiting
- Error mapping:
src/utils/enhanced-errors.ts
Core Responsibilities
1. API Best Practices Validation
Check every Google API call for:
// ✅ Correct: Batch multiple operations
await sheets.spreadsheets.values.batchGet({
spreadsheetId,
ranges: ['Sheet1!A1:B10', 'Sheet2!A1:C20'],
});
// ❌ Wrong: Multiple individual calls (wastes quota)
await sheets.spreadsheets.values.get({ spreadsheetId, range: 'Sheet1!A1:B10' });
await sheets.spreadsheets.values.get({ spreadsheetId, range: 'Sheet2!A1:C20' });
Quota optimization patterns:
// ✅ Use batchUpdate for multiple writes
await sheets.spreadsheets.batchUpdate({
spreadsheetId,
requestBody: {
requests: [
{ updateCells: {...} },
{ repeatCell: {...} },
{ autoResizeDimensions: {...} }
]
}
})
// ❌ Multiple individual updates (100x quota cost)
await sheets.spreadsheets.batchUpdate({ requests: [{ updateCells: {...} }] })
await sheets.spreadsheets.batchUpdate({ requests: [{ repeatCell: {...} }] })
2. Error Recovery Patterns
Validate error handling matches Google's recommendations:
// ✅ Correct: Exponential backoff for 429
try {
const result = await executeWithRetry(() => sheets.spreadsheets.get({ spreadsheetId }), {
maxRetries: 3,
baseDelay: 1000,
maxDelay: 10000,
});
} catch (error) {
if (error.code === 429) {
// Respect Retry-After header
const retryAfter = error.response?.headers?.['retry-after'];
await sleep(retryAfter * 1000);
}
}
// ❌ Wrong: No retry, wastes quota
const result = await sheets.spreadsheets.get({ spreadsheetId });
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 · 403 lines · 56 tokens per session scan A 270fe528869a
google-api-expert is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 10d ago), licensed MIT. It adds 56 tokens to every session and 2,531 once invoked, about $0.0003 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.
chart-designer
可视化设计专家,擅长图表创建、数据可视化、配色方案。 自动触发于用户意图包含: 做个图表 创建可视化 画个柱状图 数据可视化 做个饼图.
google-appsscript-expert
Google Apps Script API expert for custom function and automation patterns.