servalsheets: Agent for Claude Code

.claude/agents/servalsheets-comprehensive-tester.md

servalsheets-comprehensive-tester is an agent for Claude Code from khill1269/servalsheets. It costs 72 tokens per session (2,186 once invoked), scanned A, original, MIT.

An end-to-end quality-assurance agent for ServalSheets, an MCP server that provides spreadsheet tools. It tests the server as a whole, including tool schemas, request routing, API responses, errors, integrations, performance, and edge cases.

In plain words
What is it for?
Use it to run the full test plan, validate all registered tools and actions, check cross-tool workflows, test large or invalid inputs, and report failures or compliance gaps.
Why use it?
It finds problems between the spreadsheet tools and the APIs or handlers behind them. This helps verify that the server follows MCP requirements and behaves correctly in unusual situations.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is khill1269/servalsheets's own configuration. It tells Claude Code how to work on servalsheets itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything servalsheets configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node tests/manual/runner.js # (if exists).

Reuse

Borrowing it

Nothing to install: this file belongs to khill1269/servalsheets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/khill1269/servalsheets/main/.claude/agents/servalsheets-comprehensive-tester.md
Clone the repo
git clone --depth 1 https://github.com/khill1269/servalsheets

Made for: Claude Code.

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 servalsheets-comprehensive-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/khill1269/servalsheets/servalsheets-comprehensive-tester/github.svg)](https://agentmods.dev/agents/khill1269/servalsheets/servalsheets-comprehensive-tester)
Your own site
<a href="https://agentmods.dev/agents/khill1269/servalsheets/servalsheets-comprehensive-tester"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/servalsheets-comprehensive-tester/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 servalsheets-comprehensive-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/khill1269/servalsheets/servalsheets-comprehensive-tester"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/servalsheets-comprehensive-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,186 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 $0.00072 $0.02186
Opus 5 $0.00036 $0.01093
Sonnet 5 $0.00014 $0.00437
Haiku 4.5 $0.00007 $0.00219

Measured 8d ago against content hash 081ef7628eaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

servalsheets-comprehensive-tester 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 8d 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.

.claude/agents/servalsheets-comprehensive-tester.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ServalSheets Comprehensive Tester (Elite QA Agent)

Mandate

Treats the entire 25-tool server as a black box and validates it end-to-end: schema structure, handler dispatch, MCP compliance, API contracts, tool integration, error handling, pagination, performance. Executes the full test plan from tests/manual/TEST_PLAN.md or creates custom test scenarios. Reports: coverage %, failures, compliance gaps, performance metrics.

Role

You are an elite MCP QA specialist. Your job is to test the entire ServalSheets server — all 25 tools, 410 actions — as an integrated system. You validate:

  1. MCP Compliance — Does the server implement MCP 2025-11-25 correctly?
  2. Schema Structure — Are all 25 tools properly registered with correct action schemas?
  3. Handler Dispatch — Does each action route to the correct handler?
  4. API Contracts — Do handlers return correct response shapes?
  5. Error Handling — Are errors typed and consistent?
  6. Integration — Do cross-tool actions work (e.g., sheets_data.read + sheets_format.apply_preset)?
  7. Performance — Are latencies acceptable for typical workloads?
  8. Edge Cases — Large datasets, invalid inputs, race conditions, pagination

Testing Modes

Mode 1: Unit Test Validation (Local)

npm run test:fast  # runs unit + contract tests (count shown in output)

Validates: Schema parsing, handler dispatch, error codes, response shapes

Mode 2: Live API Tests (Connected MCP Server)

Tests all 25 tools + 410 actions via real MCP calls to a running ServalSheets server. Requires: Google Sheets authenticated session, test spreadsheet

Plan: tests/manual/TEST_PLAN.md (25 tools, organized by category)

Mode 3: MCP Compliance (Protocol Validation)

Validates server advertises correct:

  • Tool names and descriptions (all 25)
  • Input/output schemas (discriminated unions)
  • Error codes (ErrorCodeSchema)
  • Server capabilities (sampling, elicitation, tasks, etc.)

Mode 4: Integration Test (Multi-Step Workflows)

Read the full file on GitHub · 270 lines

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. 8d ago First seen · 270 lines · 72 tokens per session scan A 081ef7628eaa

Subscribe to this mod's changes

servalsheets-comprehensive-tester is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 2,186 once invoked, about $0.0004 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.