What is keryx CLAUDE.md?

A project instruction file for Keryx, a full-stack TypeScript framework for building APIs and MCP services with Bun. It explains the framework and its monorepo layout, where one repository contains several related packages and applications.

Use it when developing Keryx, its plugins, example applications, or documentation.

It helps coding agents understand which package or example to change and how the development environment is organized.

keryx CLAUDE.md — Instructions file for coding agents by actionhero: A project instruction file for Keryx, a full-stack TypeScript…

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/actionhero/keryx/claude-md

Clone the repo

git clone --depth 1 https://github.com/actionhero/keryx

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/actionhero/keryx/claude-md.svg)](https://agentmods.dev/instructions/actionhero/keryx/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/actionhero/keryx/claude-md"><img src="https://agentmods.dev/badge/instructions/actionhero/keryx/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,225 This file is loaded in full into every session.

When invoked 2,225 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.

Model	Per session	Once invoked
Fable 5	$0.02225	$0.02225
Opus 5	$0.01112	$0.01112
Sonnet 5	$0.00445	$0.00445
Haiku 4.5	$0.00222	$0.00222

Measured 4d ago against content hash 815dd62939a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

keryx 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 · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 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

The fullstack TypeScript framework for MCP and APIs, built on Bun. Spiritual successor to ActionHero. Monorepo with workspaces under packages/keryx/ (publishable framework), packages/plugins/* (first-party plugins like tracing and resque-admin), example/backend/ (example API server), example/frontend/ (Vite + React app), and docs/ (VitePress site). The core idea: Actions are the universal controller - they serve as HTTP endpoints, WebSocket handlers, CLI commands, background tasks, and MCP tools simultaneously.

Monorepo Structure

keryx/
  packages/
    keryx/                 # Framework package (publishable as "keryx")
      classes/             # API, Action, Channel, Connection, Initializer, etc.
      initializers/        # Framework initializers (db, redis, actions, servers, etc.)
      servers/             # WebServer (Bun.serve)
      actions/             # Built-in actions (status, swagger)
      config/              # Modular config with env overrides (logger, observability, server/web)
      middleware/          # Generic middleware (rateLimit)
      util/                # Helpers (glob, cli, config, zodMixins, oauth, generate, web*)
      templates/           # OAuth HTML + SVG + CLI generator mustache templates
      lua/                 # Redis Lua scripts
      api.ts               # Singleton + exports
      index.ts             # Package entry point (re-exports)
      keryx.ts             # CLI entry (start, generate, upgrade)
      __tests__/           # Framework-level tests
    plugins/               # First-party plugins (each is its own workspace)
      tracing/             # OpenTelemetry tracing plugin
      sentry/              # Sentry error monitoring and tracing plugin
      resque-admin/        # Web UI for inspecting Resque queues
  example/
    backend/               # Example app using keryx
      actions/             # App actions (user, session, message, channel, files)
      initializers/        # App initializer (application.ts)
      ops/                 # Business logic (UserOps, MessageOps)
      schema/              # Drizzle ORM table definitions
      channels/            # WebSocket channels
      middleware/           # App middleware (session, channel auth)
      drizzle/             # Migration SQL files
      util/                # App-specific zodMixins
      index.ts             # Sets api.rootDir, re-exports from "keryx"
      keryx.ts             # App CLI entry
      __tests__/           # App-specific tests
    frontend/              # Vite + React + Bootswatch frontend
  docs/                    # VitePress documentation site

Read the full file on GitHub · 178 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.

4d ago First seen · 178 lines · 2,225 tokens per session scan A 815dd62939a6

Subscribe to this mod's changes

keryx CLAUDE.md is an instructions file published in the GitHub repository actionhero/keryx (33 stars, last pushed 12d ago), licensed MIT. It adds 2,225 tokens to every session, about $0.0111 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 2026-08-30.

Backend and APIs Languages TypeScript ai api bun framework full-stack mcp

stitchkit AGENTS.md

Instructions for max-listov/stitchkit, covering stitchkit — agent guide, two roads — pick yours, rules, stack and commands.

max-listov/stitchkit · 4,943 tokens

nifra AGENTS.md

AGENTS.md instructions for nifrajs/nifra, covering agents.md - nifra quick reference for coding agents, 1 · define a route (typed, chainable), 2 · validate a body/query at the trust boundary (auto-422), 3 · read platform env (kv / d1 / secrets) and 4 · set status / headers, and the control-flow rule.

nifrajs/nifra · 2,352 tokens

keryx CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Project Overview

Monorepo Structure

What this file has done since we first saw it

Other instructions, from other repositories

stitchkit AGENTS.md

nifra AGENTS.md

stitchkit CLAUDE.md

eve AGENTS.md

opengeni AGENTS.md

dawnai AGENTS.md