What is sight-mcp CLAUDE.md?

Project instructions for an AI coding assistant working on a Bun-based MCP server. They describe when to consult OpenSpec files, how to implement server features, and which coding rules to follow.

Following the project's implementation rules, using Bun features, choosing server APIs, running builds and tests, and keeping OpenSpec-managed instructions up to date.

It gives the assistant project-specific guidance before it changes code, including how to handle proposals, architecture changes, and ambiguous requests.

How nightwhite/sight-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nightwhite/sight-mcp. 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/nightwhite/sight-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nightwhite/sight-mcp

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/nightwhite/sight-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nightwhite/sight-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nightwhite/sight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nightwhite/sight-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nightwhite/sight-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nightwhite/sight-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 698 This file is loaded in full into every session.

When invoked 698 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 91% copy Near-identical to another mod 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	$0.00698	$0.00698
Opus 5.5	$0.00279	$0.00279
Sonnet 5.5	$0.00140	$0.00140
Haiku 4.5	$0.00070	$0.00070

Measured 1mo ago against content hash e1570563c847, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sight-mcp 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 1mo 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.

Origin

This is a copy

91% identical to bigquery-mcp-server CLAUDE.md — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Instructions

These instructions are for AI assistants working in this project.

Always open @/openspec/AGENTS.md when the request:

Mentions planning or proposals (words like proposal, spec, change, plan)
Introduces new capabilities, breaking changes, architecture shifts, or big performance/security work
Sounds ambiguous and you need the authoritative spec before coding

Use @/openspec/AGENTS.md to learn:

How to create and apply change proposals
Spec format and conventions
Project structure and guidelines

Keep this managed block so 'openspec update' can refresh the instructions.

CLAUDE.md - Guidelines for Bun MCP Server

Implementation Rules

See mcp.mdc at first and learn how to implement a MCP Server.
Generate a appropriate package name and overwrite package.json
Some examples using setRequestHandler() to implement a tool or resource, but it's deprecated. Use server.tool() or server.resource() instead.
You can add a thrid party package if needed to meet the requirements.
You can use Bun runtime features. Bun provides many built-in functions. See bun-file.mdc, bun-test.mdc, bun-glob.mdc, bun-utils.mdc

Build Commands

bun run build - Build the MCP server executable
bun run show-package-name - Display the package name for installation
Install with: cp dist/$npm_package_name $HOME/bin/

Code Style Guidelines

Imports & Organization

Use named imports from MCP SDK: import { McpServer, ResourceTemplate } from "@modelcontextprotocol/sdk/server/mcp.js"
Group imports by external packages first, then internal modules

TypeScript & Types

Use Zod for parameter validation in tools and resources
Prefer TypeScript strict mode with explicit type annotations
Use async/await for asynchronous operations

Read the full file on GitHub · 78 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.

1mo ago First seen · 78 lines · 698 tokens per session scan A e1570563c847

Subscribe to this mod's changes

sight-mcp CLAUDE.md is an instructions file published in the GitHub repository nightwhite/sight-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 698 tokens to every session, about $0.0028 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to bigquery-mcp-server CLAUDE.md, differing in 19 lines, and is treated as a copy.

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

sight-mcp: Instructions file for Claude Code