What is openrouterai CLAUDE.md?

Error-prevention instructions for a TypeScript project that uses a DXT manifest, a package description file for an extension or tool. They require checking a solutions document and validating the manifest before changes.

Use them before implementing changes, when building or watching the project, when validating its manifest, and when documenting a newly solved error.

They collect known mistakes and their fixes so contributors do not repeat them. Early validation catches invalid configuration before building or releasing the project.

How heltonteixeira/openrouterai configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to heltonteixeira/openrouterai. 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/heltonteixeira/openrouterai/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/heltonteixeira/openrouterai

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/heltonteixeira/openrouterai/claude-md/github.svg)](https://agentmods.dev/instructions/heltonteixeira/openrouterai/claude-md)

Your own site

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

Per session 955 This file is loaded in full into every session.

When invoked 955 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	$0.00955	$0.00955
Opus 5.5	$0.00382	$0.00382
Sonnet 5.5	$0.00191	$0.00191
Haiku 4.5	$0.00096	$0.00096

Measured 2mo ago against content hash 566d86d8692a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openrouterai 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 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.

Error Prevention and Learning

Using SOLUTIONS.md as Reference

SOLUTIONS.md contains documented mistakes and their resolutions to prevent recurrence
Always consult SOLUTIONS.md before implementing changes to avoid past errors
Quick Reference Section provides critical patterns: DXT properties, platform identifiers, CLI commands
Core Standards section outlines established patterns for manifest structure, TypeScript, and environment handling
Error Resolution Process provides step-by-step validation workflow

Error Prevention Workflow

Check SOLUTIONS.md first - Review quick reference and relevant error patterns
Validate Early - Use dxt validate manifest.json before any changes
Follow Established Patterns - Use documented solutions from similar past issues
Update SOLUTIONS.md - Document new errors and their solutions for future reference

Essential Commands

Build & Development

pnpm run build - TypeScript compilation and makes dist/*.js executable
pnpm run watch - Development with live TypeScript watching
pnpm run prepare - Pre-publish build (runs automatically on npm install)

Testing

No test framework currently configured
Manual testing via MCP client integration

Package Management

Uses pnpm for package management
ES modules with Node.js 18+ required
Entry point: dist/index.js (built from src/index.ts)

Architecture Overview

Core MCP Server Structure

Entry Point: src/index.ts - Main server initialization with environment variable parsing
Tool Registration: src/tool-handlers.ts - Central dispatcher for all MCP tools with comprehensive input schemas
API Layer: src/openrouter-api.ts - OpenRouter.ai API client with rate limiting and retry logic
Caching: src/model-cache.ts - Singleton model cache with 1-hour expiry
Types: src/types.ts - Unified ToolResult interface for all tool responses

Read the full file on GitHub · 106 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.

2mo ago First seen · 106 lines · 955 tokens per session scan A 566d86d8692a

Subscribe to this mod's changes

openrouterai CLAUDE.md is an instructions file published in the GitHub repository heltonteixeira/openrouterai (64 stars, last pushed 1y ago), licensed Apache-2.0. It adds 955 tokens to every session, about $0.0038 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 2026-08-30.

openrouterai CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openrouterai CLAUDE.mdheltonteixeira/openrouterai	Instructions file	64	1y ago	Apache-2.0	A	955	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

openrouterai: Instructions file for Claude Code