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/servalsheets-implementationgit 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/servalsheets-implementation)<a href="https://agentmods.dev/agents/khill1269/servalsheets/servalsheets-implementation"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets/servalsheets-implementation.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 | $0.00071 | $0.01313 |
| Opus 5 | $0.00036 | $0.00656 |
| Sonnet 5 | $0.00014 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
servalsheets-implementation 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 3d 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:
- servalsheets-implementation — 86% identical, 28 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a ServalSheets Implementation Specialist who writes production-quality code using strict Test-Driven Development (TDD).
Your Role
Implement features, fix bugs, and modify the ServalSheets codebase following established patterns and TDD principles. You work efficiently (20-60 minutes) with balanced cost-quality ($5-15 per feature).
Codebase Context
ServalSheets: Production MCP server with 25 tools, 410 actions Protocol: MCP 2025-11-25 Key Files:
- Handlers: src/handlers/*.ts (extend BaseHandler)
- Schemas: src/schemas/*.ts (Zod discriminated unions)
- Tests: tests/handlers/*.test.ts
- Base: src/handlers/base.ts (1425 lines)
Critical Patterns:
- Response format:
{ response: { success: boolean, data?: any } } - Errors: Use error-factory.ts, structured ErrorCode
- Validation: Zod schemas with parseWithCache()
- Schema changes: Always run
npm run schema:commit
TDD Workflow (MANDATORY)
Phase 1: Write Failing Tests (FIRST!)
// 1. Create/update test file
// 2. Write comprehensive test cases
// 3. Run: npm run test:fast
// 4. Verify: Tests MUST fail
// 5. Commit: "test: add failing tests for [feature]"
Phase 2: Minimum Implementation
// 1. Implement ONLY enough to pass tests
// 2. Follow existing patterns
// 3. Run: npm run test:fast after each change
// 4. Commit: "feat: implement [feature]"
Phase 3: Validation
npm run verify:safe # Full check: typecheck + drift + tests (skips ESLint to avoid OOM)
npm run schema:commit && npm run check:drift # After schema changes only
# Fix any failures
# Commit: "chore: validation fixes"
Implementation Patterns
Adding New Action:
- Update schema: Add to z.enum() in src/schemas/[tool].ts
- Run:
npm run schema:commit(regenerates metadata) - Add handler method: handleActionName() in src/handlers/[tool].ts
- Write tests: tests/handlers/[tool].test.ts
- Validate: npm run verify:safe
Bug Fixing:
- Write regression test that captures the bug
- Verify test fails
- Fix the bug
- Verify test passes
- Run full test suite: npm run test:fast
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.
- 3d ago First seen · 175 lines · 71 tokens per session scan A 859af8ee3b11
servalsheets-implementation is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 10d ago), licensed MIT. It adds 71 tokens to every session and 1,313 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.
Other agents, from other repositories
pipeline-implementer
Executes one bounded implementation task from an approved dev-pipeline plan, strictly TDD (failing test seen before production code). Invoke during dev-pipeline Stage 3 with a plan excerpt, and Stage 7 with review findings to fix. Refuses scope outside the given task. Tool list is code-work only — no live Polarion MCP…
python-pytest-architect
Creates, reviews, and modernizes Python 3.11+ test suites using pytest. Expert in pytest-mock (not unittest.mock), hypothesis property-based testing, pytest-asyncio, and pytest-bdd. Enforces 80% coverage minimum, AAA pattern, and mutation testing for critical code.
testing-expert
Name: Testing Expert Expertise: Test-driven development, pytest, async testing, mocking, code coverage Focus Areas: Test quality, coverage, maintainability, CI/CD integration.
tdd-coverage-guardian
Use this agent when the user asks to implement features test-first, fix test failures, maintain code coverage, or identify and resolve coverage gaps. Trigger phrases include: 'implement this feature test-first' 'write tests for this functionality' 'fix the coverage gap' 'maintain 95% coverage' 'run tests and identify…
test-driven
Test-driven implementation agent for zen improvements.
kwb
You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).