relay-ai: Instructions file for Claude Code

CLAUDE.md

relay-ai CLAUDE.md is an instructions file for Claude Code from jacob-bd/relay-ai. It costs 8,565 tokens per session, scanned B, original, MIT.

Repository instructions for Relay AI, including its release process, commands, testing, and local command-line use.

In plain words
What is it for?
Use it when changing Relay AI, running a single test file, testing the command-line tool locally, building, or preparing a release.
Why use it?
It prevents common maintenance mistakes, such as publishing packages manually when automated release workflows handle publishing.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is jacob-bd/relay-ai's own configuration. It tells Claude Code how to work on relay-ai 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 relay-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jacob-bd/relay-ai. 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/jacob-bd/relay-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jacob-bd/relay-ai

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 relay-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jacob-bd/relay-ai/claude-md.svg)](https://agentmods.dev/instructions/jacob-bd/relay-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jacob-bd/relay-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/jacob-bd/relay-ai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,565 This file is loaded in full into every session.
When invoked 8,565 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.08565 $0.08565
Opus 5 $0.04283 $0.04283
Sonnet 5 $0.01713 $0.01713
Haiku 4.5 $0.00856 $0.00856

Measured 7d ago against content hash bf6a463b36d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

relay-ai CLAUDE.md scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Env isolation:** `buildChildEnv()` copies `process.env`, deletes all 17 vars in `CONFLICTING_ENV_VARS`, then sets `ANTHROPIC_BASE_URL`, `ANTHROPIC_API_KEY`, `ANTHROPIC_MODEL`. `launchClaude()` also passes `--model`. Is
CLAUDE.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 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. Note that the codebase supports Claude Code, OpenAI Codex, and Google Gemini CLI.

Docker / always-on gateway: If a user asks to run Relay AI in a container, follow docs/DOCKER.md (AI checklist + questions). That deploys Server + Admin UI only — not desktop app launch.

Release workflow

Publishing is automated by GitHub Actions (.github/workflows/publish.yml): pushing a v* tag runs typecheck + tests + build, then npm publish (auth via the RELAYAI repo secret — an npm Automation token) and creates a GitHub Release from the matching CHANGELOG.md section. Do NOT run npm publish locally — that double-publishes and fails.

To release a new version:

# 1. Land all code changes and a CHANGELOG.md "## [x.y.z]" section first (committed).
npm version patch --no-git-tag-version   # bump package.json + package-lock (use minor/major as needed)
npm run build                            # rebuild dist — VERSION is derived from package.json automatically
git add -A && git commit -m "release: vX.Y.Z"
git tag -a vX.Y.Z -m "vX.Y.Z"            # MUST be annotated (-a); see below
git push --follow-tags                   # tag push triggers CI → npm publish + GitHub Release

The tag must be annotated (git tag -a). git push --follow-tags pushes only annotated tags, so a lightweight git tag vX.Y.Z is silently left behind: the push reports main -> main, no v* ref reaches the remote, and the publish workflow never triggers. The release looks committed but nothing is published. If that happens, git tag -d vX.Y.Z && git tag -a vX.Y.Z -m "vX.Y.Z" && git push origin vX.Y.Z recovers it. Verify with git ls-remote --tags origin | grep vX.Y.Z — an annotated tag shows both refs/tags/vX.Y.Z and refs/tags/vX.Y.Z^{}.

package.json is the single source of truth for the version. Never edit src/constants.ts manually for version bumps. dist/ is committed, so rebuild it in the release commit.

Read the full file on GitHub · 223 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. 7d ago First seen · 223 lines · 8,565 tokens per session scan B bf6a463b36d1

Subscribe to this mod's changes

relay-ai CLAUDE.md is an instructions file published in the GitHub repository jacob-bd/relay-ai (173 stars, last pushed 3d ago), licensed MIT. It adds 8,565 tokens to every session, about $0.0428 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

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

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

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