What is relay CLAUDE.md?

A set of instructions for Claude Code projects that can hand suitable coding tasks to Relay, an MCP server for delegating work to another agent.

Use it for scaffolding, independent functions, first drafts of tests or documentation, and large mechanical changes.

It clarifies which routine tasks may be delegated and which decisions must stay with the main agent. This helps avoid delegating architecture, broad debugging, or final review.

How orhanucok/relay configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to orhanucok/relay. 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/orhanucok/relay/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/orhanucok/relay

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/orhanucok/relay/claude-md/github.svg)](https://agentmods.dev/instructions/orhanucok/relay/claude-md)

Your own site

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

Per session 133 This file is loaded in full into every session.

When invoked 133 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	$0.00133	$0.00133
Opus 5.5	$0.00053	$0.00053
Sonnet 5.5	$0.00027	$0.00027
Haiku 4.5	$0.00013	$0.00013

Measured 2mo ago against content hash 4a6f1690554f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

relay 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 · 18 lines

What it actually says

Relay rules

The Relay MCP server is available. Use the delegate tool for:

Boilerplate / scaffolding code; independent, well-defined functions
First drafts of tests and documentation
Format conversion; large mechanical refactors

Do these YOURSELF (do not delegate):

Architecture and design decisions
System-wide, multi-context debugging
Merging all results and the final review
Direct communication with the user

Before delegating, ask:

Is this piece independent?
Can a cheaper model do it correctly?
Is reviewing the result cheaper than writing it from scratch? If unsure, do it yourself.

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 · 18 lines · 133 tokens per session scan A 4a6f1690554f

Subscribe to this mod's changes

relay CLAUDE.md is an instructions file published in the GitHub repository orhanucok/relay (0 stars, last pushed 4mo ago), licensed MIT. It adds 133 tokens to every session, about $0.0005 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.

Building agents

relay CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
relay CLAUDE.mdorhanucok/relay	Instructions file	0	4mo ago	MIT	A	133	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

relay: Instructions file for Claude Code