What is servalsheets-v2 CLAUDE.md?

Claude Code instructions for ServalSheets, a TypeScript MCP server that works with Google Sheets. They describe the project structure, live notes, request-processing pipeline, documentation, and rules for verifying claims.

Use them when developing ServalSheets, tracing Google Sheets tool requests, checking project state, or documenting and verifying implementation changes.

They give the coding agent the project context and required workflow before it changes code. The file also limits its own size and points to separate architecture and state documents.

How khill1269/servalsheets-v2 configures Claude Code

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.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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/khill1269/servalsheets-v2/claude-md.svg)](https://agentmods.dev/instructions/khill1269/servalsheets-v2/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/khill1269/servalsheets-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/khill1269/servalsheets-v2/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,947 This file is loaded in full into every session.

When invoked 2,947 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02947	$0.02947
Opus 5	$0.01473	$0.01473
Sonnet 5	$0.00589	$0.00589
Haiku 4.5	$0.00295	$0.00295

Measured 7d ago against content hash 66b967bd26ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

servalsheets-v2 CLAUDE.md 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 7d 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.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Rules (ServalSheets)

Size cap: 300 lines. If this file exceeds 300 lines, move content to docs/. Architecture reference: docs/development/ARCHITECTURE.md

Live State & Session Context

Live project state (auto-generated): @.serval/state.md Session notes (decisions, next steps): @.serval/session-notes.md Codebase deep context (all tools, MCP, API patterns): @docs/development/CODEBASE_CONTEXT.md Feature roadmap (P4 differentiators): @docs/development/FEATURE_PLAN.md

Project Overview

ServalSheets is a production-grade MCP server for Google Sheets with 25 tools and 407 actions. Runtime: Node.js + TypeScript (strict). See src/schemas/index.ts for authoritative counts.

Core Pipeline

MCP Request → src/server.ts:handleToolCall()
  → src/mcp/registration/tool-handlers.ts:createToolCallHandler()
    → normalizeToolArgs() → Zod validation → handler.executeAction()
      → src/services/google-api.ts (auto-retry + circuit breaker)
    → buildToolResponse() → CallToolResult

Full 4-layer trace with line numbers: docs/development/ARCHITECTURE.md

Non-negotiable Workflow

Verify before claiming — every fact needs file:line OR command → output
Trace execution paths — prove reachability from entrypoint (STDIO/HTTP/Remote)
No "fixes" without failing proof — reproduce with script or failing test first
Minimal change policy — ≤3 src/ files unless tests require more; no refactors while debugging
No silent fallbacks — never return {} without logging; use ErrorCode enum
Dead code claims need proof — run npm run validate:dead-code <file> <start> <end>
Schema-handler alignment — run npm run validate:alignment; deviations must be in src/schemas/handler-deviations.ts
Audit docs must validate — npm run validate:audit with .github/AUDIT_TEMPLATE.md format

Verification (single canonical reference)

# Before every commit
npm run verify              # Full pipeline (typecheck + lint + test + drift + checks)
npm run verify:safe         # Skips lint (use when ESLint OOMs in low-memory envs)

# After schema changes (ONE command)
npm run schema:commit       # Regenerate metadata + verify + test + stage

# Quick checks (< 15 seconds each)
npm run check:drift         # Metadata sync
npm run test:fast           # Unit + contract tests
npm run typecheck           # TypeScript strict mode

# Individual checks
npm run check:placeholders  # No TODO/FIXME in src/
npm run check:debug-prints  # No console.log in handlers
npm run check:silent-fallbacks  # No silent {} returns
npm run validate:alignment  # Schema-handler alignment
npm run validate:audit      # Audit document validation

# Full gate pipeline
npm run gates               # G0-G5 validation gates
npm run verify:build        # Build + validate + smoke

Read the full file on GitHub · 273 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.

7d ago First seen · 273 lines · 2,947 tokens per session scan A 66b967bd26ef

Subscribe to this mod's changes

servalsheets-v2 CLAUDE.md is an instructions file published in the GitHub repository khill1269/servalsheets-v2 (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,947 tokens to every session, about $0.0147 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.

Documents Spreadsheets

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

servalsheets-v2: Instructions file for Claude Code