What is happyclaw CLAUDE.md?

Repository instructions for HappyClaw, a TypeScript plugin that connects AI command-line sessions such as Claude Code, Codex, and Gemini to OpenClaw. It allows those sessions to be controlled remotely through Telegram or Discord.

Use it to install dependencies, build or type-check HappyClaw, run all or selected tests, inspect its session-provider design, or install the plugin into OpenClaw.

It provides the project overview, installation and build commands, testing commands, and details about its provider implementations. This helps an agent work on the plugin without reconstructing its setup from scratch.

How rwmjhb/happyclaw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rwmjhb/happyclaw. 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/rwmjhb/happyclaw/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rwmjhb/happyclaw

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/rwmjhb/happyclaw/claude-md/github.svg)](https://agentmods.dev/instructions/rwmjhb/happyclaw/claude-md)

Your own site

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

Per session 1,564 This file is loaded in full into every session.

When invoked 1,564 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	$0.01564	$0.01564
Opus 5	$0.00782	$0.00782
Sonnet 5	$0.00313	$0.00313
Haiku 4.5	$0.00156	$0.00156

Measured 9d ago against content hash ddf3732361b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

happyclaw 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 9d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 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

HappyClaw is an OpenClaw Plugin that bridges AI CLI sessions (Claude Code, Codex, Gemini) into OpenClaw's tool system, enabling remote control from Telegram or Discord. It uses an SDK-first approach with PTY fallback.

Primary language: TypeScript (ESM, strict mode) Runtime: Node.js Package manager: pnpm

Commands

# Install dependencies
pnpm install

# Build (TypeScript → dist/)
pnpm build

# Type-check without emitting
pnpm typecheck

# Run all tests
pnpm test

# Run a single test file
npx vitest run tests/unit/session-manager.test.ts

# Run tests matching a pattern
npx vitest run -t "spawn"

# Watch mode
pnpm test:watch

# Coverage (thresholds: 70% statements/functions/lines, 60% branches)
pnpm test:coverage

# Install plugin into OpenClaw
openclaw plugins install --link /path/to/happyclaw

Architecture

Provider Abstraction

Three providers implement the SessionProvider interface (src/types/index.ts):

Provider	File	Mode	How it works
`ClaudeSDKProvider`	`src/providers/claude-sdk.ts`	SDK `query()` (remote) / CLI `spawn` with stdio inherit (local)	Uses `@anthropic-ai/claude-agent-sdk`. Remote mode streams structured JSON; local mode gives native terminal UX.
`CodexMCPProvider`	`src/providers/codex-mcp.ts`	MCP Client → `codex mcp-server`	Two-tool pattern: `codex` (start) + `codex-reply` (continue). State machine: `connecting→working→idle→stopped`.
`GenericPTYProvider`	`src/providers/generic-pty.ts`	node-pty + @xterm/headless	For CLIs without SDKs (e.g., Gemini). Parses terminal output via configurable `ParserRuleSet`.

Core Components

SessionManager (src/session-manager.ts) — Central session lifecycle: spawn, resume, read (cursor-paginated), switchMode (state machine: running→draining→switching→running), stop. Enforces ACL ownership, cwd whitelist, session limits. Emits message, event, sessionEnd, stateTransition.
EventBus (src/event-bus.ts) — Debounced event routing with priority queue (permission_request > error > task_complete > info).
TelegramPushAdapter (src/push/telegram-push-adapter.ts) — Zero-token push: streams Claude output directly to Telegram Bot API via debounced batches. Subscribes to SessionManager messages + EventBus events.
AsyncQueue<T> (src/types/index.ts) — Push-based async iterable for feeding SDKUserMessage into SDK query(). Must push initialPrompt BEFORE starting the query to avoid deadlock.

Read the full file on GitHub · 116 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.

9d ago First seen · 116 lines · 1,564 tokens per session scan A ddf3732361b2

Subscribe to this mod's changes

happyclaw CLAUDE.md is an instructions file published in the GitHub repository rwmjhb/happyclaw (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,564 tokens to every session, about $0.0078 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.

Building agents

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 · 5,153 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

happyclaw: Instructions file for Claude Code