pipelex-mcp CLAUDE.md

pipelex-mcp CLAUDE.md is an instructions file for coding agents from Pipelex/pipelex-mcp. It costs 16,549 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Claude Code, an AI coding assistant, working on the Pipelex MCP project. They describe the project, its commands, architecture, and checks for changes in its API.

In plain words
What is it for?
Running project commands, checking API drift, validating methods and inputs, and understanding how its MCP servers expose durable runs.
Why use it?
They give the coding assistant the local context needed to work consistently in this repository and catch mismatches with the validation API.

Instructions file

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/pipelex/pipelex-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/Pipelex/pipelex-mcp

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 pipelex-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pipelex/pipelex-mcp/claude-md.svg)](https://agentmods.dev/instructions/pipelex/pipelex-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pipelex/pipelex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/pipelex/pipelex-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 16,549 This file is loaded in full into every session.
When invoked 16,549 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.

ModelPer sessionOnce invoked
Fable 5 $0.16549 $0.16549
Opus 5 $0.08275 $0.08275
Sonnet 5 $0.03310 $0.03310
Haiku 4.5 $0.01655 $0.01655

Measured 4d ago against content hash 2f18ccff348a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pipelex-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 4d 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 · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 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.

Workspace-level guidance lives in ../CLAUDE.md (Pipelex multi-repo workspace). This file covers only what is specific to pipelex-mcp.

What this repo is

pipelex-mcp exposes registered-method discovery, MTHDS validation, inputs projection and preparation, and durable method runs to MCP hosts. It ships as two servers from one capability core (see the Architecture section): a hosted Skybridge console for remote-connector hosts (ChatGPT, claude.ai, Cowork) and a local workshop stdio server distributed on npm as @pipelex/mcp for coding-agent hosts (Claude Code, Codex, Cursor). Both register the same MCP tools — mthds_list_methods, mthds_validate, mthds_inputs_template, mthds_codegen, mthds_prepare_inputs, and the mthds_run / mthds_run_status / mthds_run_results durable-run family — plus one per-shell tool on each side: the console-only mthds_upload_attachments, which turns a file the user attached in the chat into a run-ready pipelex-storage:// reference (ChatGPT's Apps runtime is the only host that substitutes the attachment), and the workshop-only mthds_download_artifacts, which saves a completed run's produced files under the server's working directory (see the Architecture section for both). mthds_list_methods is the source-free name/intent → canonical-id bridge into the existing current-content validate → inputs-template → run flow. An assistant that already holds .mthds file contents (or, on the workshop, their on-disk paths) calls mthds_validate for a stable, structured verdict it can use to explain and repair diagnostics, mthds_inputs_template for a fill-in template of a pipe's declared inputs, mthds_prepare_inputs to turn filled file-bearing inputs run-ready (uploading assets to Pipelex storage on the workshop; pass-through only on the console), mthds_codegen to project the method's concept set into typed code (ts-zod, python-pydantic, python-structures — the target chosen from the project's context) handed back verbatim with its codegen.lock, and the run family to execute a method durably. On a positive validation verdict the mthds_validate tool ships a Skybridge view, run-graph, that renders the method graph interactively with @pipelex/mthds-ui's GraphViewer (hosted console only — the workshop is tools-first, no views); mthds_list_methods, mthds_inputs_template, mthds_codegen, mthds_prepare_inputs, and the status/results tools are plain tools with no view.

Read the full file on GitHub · 193 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. 4d ago First seen · 193 lines · 16,549 tokens per session scan A 2f18ccff348a

Subscribe to this mod's changes

pipelex-mcp CLAUDE.md is an instructions file published in the GitHub repository Pipelex/pipelex-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 16,549 tokens to every session, about $0.0827 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.

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 · 5,182 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

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

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

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