contract-mcp: Instructions file for Claude Code

CLAUDE.md

contract-mcp CLAUDE.md is an instructions file for Claude Code from adaniki-dev/contract-mcp. It costs 786 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for contract-mcp, an MCP server that uses structured YAML files to describe a software project for AI agents. It covers the project’s architecture, development workflow, and commands.

In plain words
What is it for?
Use it when developing contract-mcp: define features in YAML, derive tests using TDD—writing tests before implementation—and organise code according to the documented architecture.
Why use it?
It gives agents a defined way to understand project structure and requires tests and contracts to stay aligned with the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is adaniki-dev/contract-mcp's own configuration. It tells Claude Code how to work on contract-mcp 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 contract-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adaniki-dev/contract-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/adaniki-dev/contract-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/adaniki-dev/contract-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.

agentmods badge for contract-mcp CLAUDE.md

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

agentmods 80×15 button for contract-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/adaniki-dev/contract-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/adaniki-dev/contract-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 786 This file is loaded in full into every session.
When invoked 786 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 $0.00786 $0.00786
Opus 5.5 $0.00314 $0.00314
Sonnet 5.5 $0.00157 $0.00157
Haiku 4.5 $0.00079 $0.00079

Measured 2mo ago against content hash cdbd2c74d741, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

contract-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 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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

contract-mcp

MCP server que funciona como linter de contratos para AI. Agentes AI usam o MCP ao invés de ls/path para entender projetos através de contratos YAML estruturados.

Stack

  • Runtime: Bun
  • Linguagem: TypeScript (strict)
  • Protocolo: MCP via @modelcontextprotocol/sdk (stdio transport)
  • Parsing: oxc-parser (JS/TS AST), es-module-lexer (análise de imports)
  • Contratos: YAML (input), XML (output para AI)

Arquitetura

Feature Sliced Design adaptado para tooling:

shared ← entities ← features ← app
  • shared/ — sem lógica de negócio: helpers, tipos, config
  • entities/ — modelos de domínio: contract, dependency-graph
  • features/ — casos de uso: compiler, validator, indexer, dashboard
  • app/ — composição: MCP server, registro de tools

Regra: imports só descem na hierarquia. Features nunca importam entre si — comunicam via entities.

Workflow de Desenvolvimento

contrato YAML → testes (TDD) → código
  1. Escrever/atualizar o contrato YAML da feature
  2. Derivar testes do contrato (rules, exports, tipos)
  3. Implementar até os testes passarem
  4. Nenhum código sem contrato. Nenhuma mudança de contrato sem atualizar testes.

Comandos

bun install          # instalar deps
bun test             # rodar todos os testes
bun test --filter X  # rodar testes de uma feature
bun run dev          # MCP server em dev (stdio)
bun run build        # typecheck + bundle
tsc --noEmit         # typecheck apenas

Convenções

  • Arquivos: kebab-case.ts
  • Tipos: PascalCase
  • Funções/variáveis: camelCase
  • Exports: sempre via barrel index.ts por slice
  • Erros: pattern Result<T, E> — nunca throw para erros esperados
  • Testes: colocados junto à implementação (*.test.ts)
  • Contratos: contracts/*.contract.yaml
  • Output AI: XML válido — nunca JSON
  • Sem any — TypeScript strict sem exceções

Contratos

Schema em contracts/_schema/feature.schema.yaml. Cada feature tem um .contract.yaml que define:

Read the full file on GitHub · 98 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 · 98 lines · 786 tokens per session scan A cdbd2c74d741

Subscribe to this mod's changes

contract-mcp CLAUDE.md is an instructions file published in the GitHub repository adaniki-dev/contract-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 786 tokens to every session, about $0.0031 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 2026-09-01.

Related

contract-mcp CLAUDE.md compared with instructions from other repositories

contract-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
contract-mcp CLAUDE.mdadaniki-dev/contract-mcpInstructions file07mo agoMITA786Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150kyesterdayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot