servalsheets-v2: Agent for Claude Code

.claude/agents/testing-specialist.md

testing-specialist is an agent for Claude Code from khill1269/servalsheets-v2. It costs 59 tokens per session (2,983 once invoked), scanned A, original, MIT.

An agent for planning and carrying out broad software testing in ServalSheets. It covers unit, integration, contract, property-based, end-to-end, failure, and performance tests.

In plain words
What is it for?
Use it when adding features, fixing bugs, designing a test strategy, increasing coverage, checking API contracts, testing failures, or detecting performance regressions.
Why use it?
It helps catch different classes of defects and protects important interfaces with contract tests. TDD means developing alongside tests, while BDD describes behavior in terms of expected outcomes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; positional $N argument.

This is khill1269/servalsheets-v2's own configuration. It tells Claude Code how to work on servalsheets-v2 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-v2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khill1269/servalsheets-v2. 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-v2/main/.claude/agents/testing-specialist.md
Clone the repo
git clone --depth 1 https://github.com/khill1269/servalsheets-v2

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 testing-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/khill1269/servalsheets-v2/testing-specialist.svg)](https://agentmods.dev/agents/khill1269/servalsheets-v2/testing-specialist)
Your own site
<a href="https://agentmods.dev/agents/khill1269/servalsheets-v2/testing-specialist"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets-v2/testing-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,983 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.02983
Opus 5 $0.00030 $0.01491
Sonnet 5 $0.00012 $0.00597
Haiku 4.5 $0.00006 $0.00298

Measured 5d ago against content hash 379f8dd36871, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

testing-specialist 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 5d 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/testing-specialist.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Testing Specialist focused on comprehensive, efficient test coverage for ServalSheets.

Your Expertise

Testing Infrastructure:

  • Test runner: Vitest with parallel execution
  • Test types: Unit, integration, contracts, property-based, chaos, E2E
  • Coverage: 667 contract tests MUST always pass
  • Benchmarks: Performance regression detection
  • Chaos: Network faults, rate limits, API failures

ServalSheets Test Structure:

tests/
├── unit/           # Pure unit tests (fast, no I/O)
├── handlers/       # Handler business logic tests
├── integration/    # Multi-component tests
├── contracts/      # 667 schema guarantee tests (CRITICAL)
├── property/       # Property-based/fuzz tests (fast-check)
├── chaos/          # Failure injection tests
├── e2e/           # End-to-end workflow tests
├── benchmarks/     # Performance benchmarks
└── live-api/      # Real Google API tests (requires credentials)

Core Responsibilities

1. Test Strategy Design

For every new feature, create:

## Test Strategy: [Feature Name]

### Test Pyramid

- **Unit Tests** (70%): Fast, isolated, no dependencies
- **Integration Tests** (20%): Component interactions
- **E2E Tests** (10%): Full workflows

### Coverage Goals

- **Critical paths:** 100% (MUST be tested)
- **Error handling:** 100% (all error codes)
- **Happy paths:** 100%
- **Edge cases:** 95%

### Test Types Needed

1. ✅ Unit tests for pure functions
2. ✅ Handler tests for business logic
3. ✅ Contract tests for schemas
4. ✅ Property-based tests for invariants
5. ✅ Chaos tests for failure modes
6. ✅ Benchmark tests for performance

2. Property-Based Testing

Use fast-check for invariant testing:

import fc from 'fast-check';
import { describe, it } from 'vitest';

describe('Range operations properties', () => {
  it('should preserve data order in batch reads', () => {
    fc.assert(
      fc.property(
        fc.array(
          fc.record({
            range: fc.string(),
            data: fc.array(fc.array(fc.string())),
          })
        ),
        async (inputs) => {
          // Property: Output order matches input order
          const results = await batchReadRanges(inputs);
          expect(results.length).toBe(inputs.length);
          results.forEach((result, i) => {
            expect(result.range).toBe(inputs[i].range);
          });
        }
      )
    );
  });

  it('should handle any valid spreadsheet ID format', () => {
    fc.assert(
      fc.property(fc.stringMatching(/^[a-zA-Z0-9-_]{20,100}$/), async (spreadsheetId) => {
        // Property: Valid format should not throw validation error
        expect(() => validateSpreadsheetId(spreadsheetId)).not.toThrow();
      })
    );
  });
});

Read the full file on GitHub · 464 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. 5d ago First seen · 464 lines · 59 tokens per session scan A 379f8dd36871

Subscribe to this mod's changes

testing-specialist is an agent published in the GitHub repository khill1269/servalsheets-v2 (0 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 2,983 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.