mcp-contrast: Instructions file for Claude Code

CLAUDE.md

mcp-contrast CLAUDE.md is an instructions file for Claude Code from Contrast-Security-OSS/mcp-contrast. It costs 8,925 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for an MCP server that lets AI agents access and analyze vulnerability data from Contrast Security.

In plain words
What is it for?
Use them when modifying the server, understanding its security-data integration, reviewing repository guidance, or preparing changes without bypassing git hooks.
Why use it?
They explain the project context and enforce development rules, including keeping the repository’s automated checks active.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Contrast-Security-OSS/mcp-contrast's own configuration. It tells Claude Code how to work on mcp-contrast 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 mcp-contrast configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is includeBuild("../mcp-contrast") {.

Reuse

Borrowing it

Nothing to install: this file belongs to Contrast-Security-OSS/mcp-contrast. 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/Contrast-Security-OSS/mcp-contrast/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Contrast-Security-OSS/mcp-contrast

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 mcp-contrast CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/contrast-security-oss/mcp-contrast/claude-md.svg)](https://agentmods.dev/instructions/contrast-security-oss/mcp-contrast/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/contrast-security-oss/mcp-contrast/claude-md"><img src="https://agentmods.dev/badge/instructions/contrast-security-oss/mcp-contrast/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,925 This file is loaded in full into every session.
When invoked 8,925 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.08925 $0.08925
Opus 5 $0.04463 $0.04463
Sonnet 5 $0.01785 $0.01785
Haiku 4.5 $0.00893 $0.00893

Measured 8d ago against content hash a8ddabd06ace, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-contrast CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

The workflows below use the **pr-tools** plugin (`/pr-tools:*` commands). If those skills aren't available, ask permission, then have the user run:

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 514 lines

How it starts

The opening of the file, as written. The whole thing — 514 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.

Project Overview

This is an MCP (Model Context Protocol) server for Contrast Security that enables AI agents to access and analyze vulnerability data from Contrast's security platform. It serves as a bridge between Contrast Security's API and AI tools like Claude, enabling automated vulnerability remediation and security analysis.

Communication style

Be concise. Lead with the answer or conclusion, then supporting detail only if needed. Skip restating the request, unnecessary preamble, and padding.

Repo context

See REPO-CONTEXT.md for domain definitions, architecture notes, and the planning checklist.

Git Hooks

ABSOLUTE RULE: NEVER skip git hooks. Do not use --no-verify, --no-gpg-sign, SKIP_PUSH_GATE=1, or any other mechanism to bypass pre-commit, pre-push, or any other git hook. No exceptions. No shortcuts. If a hook fails, fix the underlying problem. A skipped hook caused a CI build failure; this rule exists to prevent that from ever happening again. If you skip a hook, you have made an error.

Uncommitted Changes

Never discard uncommitted work without explicit permission. When switching branches, git stash is acceptable only if you git stash pop immediately after the checkout completes. Stashing and leaving changes buried in the stash list is not allowed. If the pop fails (conflict, etc.), resolve it right away and restore the changes. The user's working-tree state must survive branch switches intact.

Branching and PR Requirements

All code changes must be made on a feature branch. Never commit directly to main. Never use raw git checkout -b or gh pr create when pr-tools skills are loaded.

Default to stacking. When unmerged feature branches exist, create new branches stacked on the tip of the current stack using /pr-tools:create-stacked-branch. Only branch off main when the user explicitly says so. If unsure which branch is the stack tip, check with the user rather than defaulting to main.

Read the full file on GitHub · 514 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. 8d ago First seen · 514 lines · 8,925 tokens per session scan A a8ddabd06ace

Subscribe to this mod's changes

mcp-contrast CLAUDE.md is an instructions file published in the GitHub repository Contrast-Security-OSS/mcp-contrast (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 8,925 tokens to every session, about $0.0446 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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

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

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens