What is conduit_mcp CLAUDE.md?

Repository guidance for Claude Code when working on ConduitMCP, an Elixir library for building Model Context Protocol (MCP) servers that connect tools and data to AI applications.

Building, testing, formatting, linting, analyzing, documenting, benchmarking, and checking code coverage for ConduitMCP.

It puts the project overview, architecture, request flow, and standard development commands in one place, so an agent can work consistently in the repository.

How nyo16/conduit_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nyo16/conduit_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/nyo16/conduit_mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nyo16/conduit_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/nyo16/conduit_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nyo16/conduit_mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nyo16/conduit_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nyo16/conduit_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/nyo16/conduit_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nyo16/conduit_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,570 This file is loaded in full into every session.

When invoked 4,570 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.

Model	Per session	Once invoked
Fable 5.1	$0.04570	$0.04570
Opus 5.5	$0.01828	$0.01828
Sonnet 5.5	$0.00914	$0.00914
Haiku 4.5	$0.00457	$0.00457

Measured 19d ago against content hash 1675a4335eac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

conduit_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 19d 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 · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 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

ConduitMCP is an Elixir library implementing the Model Context Protocol (MCP) in two eras at once: modern 2026-07-28 (stateless, per-request _meta) and legacy 2025-11-25 / 2025-06-18 (initialize + sessions). It lets developers build MCP servers that expose tools, resources, and prompts to LLM applications like Claude Desktop and VS Code, and ships a production MCP client (ConduitMcp.Client). The library is published on Hex as conduit_mcp.

Build & Test Commands

mix deps.get              # Install dependencies
mix compile               # Compile
mix test                  # Run all tests (~2,400: 2,304 tests, 61 doctests, 40 properties; includes :integration and :stdio)
mix test test/conduit_mcp/dsl_test.exs           # Run a single test file
mix test test/conduit_mcp/dsl_test.exs:42        # Run a specific test line
mix format                # Format code
mix credo                 # Lint
mix dialyzer              # Static analysis (slow first run)
mix docs                  # Generate docs
mix bench                 # Run all benchmarks
mix bench validation      # Run a specific benchmark
mix bench --list          # List available benchmarks
MIX_ENV=test mix coveralls.html  # Coverage report

Requires Elixir ~> 1.18. No config directory exists; validation config is set via Application.put_env(:conduit_mcp, :validation, [...]) in tests or application config.

CI runs on Elixir 1.18.3 / OTP 27.2 (ELIXIR_VERSION/OTP_VERSION in .github/workflows/ci.yml; Dialyzer with MIX_ENV=dev). A clean Dialyzer on a newer OTP proves nothing for CI: OTP 28+ changed opaque-type checking, so run it on the CI toolchain too, with its own build path, e.g. MIX_BUILD_PATH=/tmp/cm_build_118_dev MIX_ENV=dev mix dialyzer under Elixir 1.18.3/OTP 27.2. In particular, don't pass Mint.HTTP.t() or Secret.t() (both opaque) through ||, guards or the Mint.HTTP union; use Mint.HTTP1 and an explicit nil match.

Read the full file on GitHub · 133 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.

19d ago Changed · +26 lines · +2,183 tokens per session 1675a4335eac
1mo ago Changed · +35 tokens per session acac37ecad11
2mo ago First seen · 107 lines · 2,352 tokens per session scan A 018847cbe59c

Subscribe to this mod's changes

conduit_mcp CLAUDE.md is an instructions file published in the GitHub repository nyo16/conduit_mcp (11 stars, last pushed 19d ago), licensed Apache-2.0. It adds 4,570 tokens to every session, about $0.0183 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.

LLM ai elixir mcp model-context-protocol-server

conduit_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
conduit_mcp CLAUDE.mdnyo16/conduit_mcp	Instructions file	11	19d ago	Apache-2.0	A	4,570	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

conduit_mcp: Instructions file for Claude Code