servalsheets: Instructions file for Claude Code

CLAUDE.md

servalsheets CLAUDE.md is an instructions file for Claude Code from khill1269/servalsheets. It costs 4,253 tokens per session, scanned A, original, MIT.

A project-specific instruction file for Claude Code, the coding assistant, describing how to work on the ServalSheets codebase. It covers the project structure, live session information, and required development workflow.

In plain words
What is it for?
Use it when developing or reviewing ServalSheets, a Node.js and TypeScript server that connects tools to Google Sheets. It helps guide work through request handling, validation, services, and project documentation.
Why use it?
It gives the assistant the rules and context needed to make changes consistently in this repository. It also points to large reference files and tells it when to load them.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

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 →

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.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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/khill1269/servalsheets/claude-md"><img src="https://agentmods.dev/badge/instructions/khill1269/servalsheets/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,253 This file is loaded in full into every session.
When invoked 4,253 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04253 $0.04253
Opus 5.5 $0.01701 $0.01701
Sonnet 5.5 $0.00851 $0.00851
Haiku 4.5 $0.00425 $0.00425

Measured 2mo ago against content hash a0d92ea0fb29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

servalsheets 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 2mo 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 · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 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

Load on demand — do NOT auto-load these large files:

  • Session notes (20KB): .serval/session-notes.md — read only the section matching current task
  • Codebase context (80KB+): docs/development/CODEBASE_CONTEXT.md — load only handler/service section matching current module
  • Feature roadmap (40KB+): docs/development/FEATURE_PLAN.md — load only the section for current feature
  • Dispatch map (JSON): .serval/routing-map.json — query by tool.action key (e.g. sheets_data.read)

Project Overview

ServalSheets is a production-grade MCP server for Google Sheets with 25 tools and 410 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

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

Read the full file on GitHub · 303 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. 2mo ago First seen · 303 lines · 4,253 tokens per session scan A a0d92ea0fb29

Subscribe to this mod's changes

servalsheets CLAUDE.md is an instructions file published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,253 tokens to every session, about $0.0170 per session on Opus 5.5. 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.

Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens