What is VSC-MCPServer CLAUDE.md?

A set of Claude Code instructions for a specific VS Code extension project. It defines repository rules, GitHub practices, commit and branch naming, testing, and extension-development guidance.

Use it when working on the specified repository to follow its branching, pull-request, issue, commit, testing, and VS Code extension rules.

It gives coding agents consistent project rules, helping prevent direct changes to the main branch, incomplete validation, and undocumented project conventions.

VSC-MCPServer CLAUDE.md — Instructions file by CodingWithCalvin

Install

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.

agentmods

npx agentmods add instructions/codingwithcalvin/vsc-mcpserver/claude-md

Clone the repo

git clone --depth 1 https://github.com/CodingWithCalvin/VSC-MCPServer

Per session 1,123 This file is loaded in full into every session.

When invoked 1,123 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01123	$0.01123
Opus 5	$0.00562	$0.00562
Sonnet 5	$0.00225	$0.00225
Haiku 4.5	$0.00112	$0.00112

Measured yesterday against content hash 4b81d612b80b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

VSC-MCPServer 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 yesterday.

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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Critical Rules

These rules override all other instructions:

NEVER commit directly to main - Always create a feature branch and submit a pull request
Conventional commits - Format: type(scope): description
GitHub Issues for TODOs - Use gh CLI to manage issues, no local TODO files. Use conventional commit format for issue titles
Pull Request titles - Use conventional commit format (same as commits)
Branch naming - Use format: type/scope/short-description (e.g., feat/tools/new-tool)
Working an issue - Always create a new branch from an updated main branch
Check branch status before pushing - Verify the remote tracking branch still exists. If a PR was merged/deleted, create a new branch from main instead
Write tests - All new/refactored code requires tests where applicable
Run validation before commits - Run npm run build and npm run test and verify no errors before committing
No co-authors - Do not add co-author information on commits or pull requests
No "generated by" statements - Do not add generated-by statements on pull requests

GitHub CLI Commands

gh issue list                    # List open issues
gh issue view <number>           # View details
gh issue create --title "type(scope): description" --body "..."
gh issue close <number>

Conventional Commit Types

Type	Description
`feat`	New feature
`fix`	Bug fix
`docs`	Documentation only
`refactor`	Code change that neither fixes a bug nor adds a feature
`test`	Adding or updating tests
`chore`	Maintenance tasks
`perf`	Performance improvement
`ci`	CI/CD changes

VS Code Extension Development Rules

Project Structure:

Extension source in src/ directory
Main entry point: src/extension.ts
Tools in src/tools/
Server implementation in src/server/
Tests co-located with source files (*.test.ts)

Read the full file on GitHub · 138 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.

yesterday First seen · 138 lines · 1,123 tokens per session scan A 4b81d612b80b

Subscribe to this mod's changes

VSC-MCPServer CLAUDE.md is an instructions file published in the GitHub repository CodingWithCalvin/VSC-MCPServer (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,123 tokens to every session, about $0.0056 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.

Git and workflow Testing extension visualstudiocode vsix

VSC-MCPServer CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Critical Rules

GitHub CLI Commands

Conventional Commit Types

VS Code Extension Development Rules

What this file has done since we first saw it

Other instructions, from other repositories

VS-MCPServer CLAUDE.md

vite-vue3-browser-extension-v3 AGENTS.md

vite-vue3-browser-extension-v3 copilot-instructions.md

pi-ask AGENTS.md

VideoAdGuard CLAUDE.md

pi-rules AGENTS.md