agentmods.dev

alphaclaw AGENTS.md

alphaclaw AGENTS.md is an instructions file for Codex, OpenCode from chrysb/alphaclaw. It costs 3,891 tokens per session, scanned A, original, MIT.

A project guide for AlphaClaw, the setup and operations layer around OpenClaw. It describes the project structure, how its server manages OpenClaw, and its main integrations and technologies.

In plain words
What is it for?
Use it when working on AlphaClaw's command-line entry point, server, setup interface, watchdog recovery, gateway proxying, or channel integrations.
Why use it?
It gives the coding agent the background needed to navigate an unfamiliar project and understand how its parts fit together.

Instructions file for CodexOpenCode

not rated 1.5k +2 3d ago A scan 3,891 tokens original MIT
View the source file chrysb/alphaclaw
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/chrysb/alphaclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/chrysb/alphaclaw

Made for: Codex, OpenCode.

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 alphaclaw AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrysb/alphaclaw/agents-md.svg)](https://agentmods.dev/instructions/chrysb/alphaclaw/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/chrysb/alphaclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/chrysb/alphaclaw/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,891 This file is loaded in full into every session.
When invoked 3,891 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.

ModelPer sessionOnce invoked
Fable 5 $0.03891 $0.03891
Opus 5 $0.01946 $0.01946
Sonnet 5 $0.00778 $0.00778
Haiku 4.5 $0.00389 $0.00389

Measured 3d ago against content hash b4fdcdb78855, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alphaclaw AGENTS.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 3d 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.

AGENTS.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Overview

AlphaClaw Project Context

AlphaClaw is the ops and setup layer around OpenClaw. It provides a browser-based setup UI, gateway lifecycle management, watchdog recovery flows, and integrations (for example Telegram, Discord, Google Workspace, and webhooks) so users can operate OpenClaw without manual server intervention.

Understanding OpenClaw

If you need to understand the internals of OpenClaw, you can inspect the code at ~/Projects/openclaw/src

Architecture At A Glance

  • bin/alphaclaw.js: CLI entrypoint and lifecycle command surface.
  • lib/server: Express server, authenticated setup APIs, watchdog APIs, channel integrations, and proxying to the OpenClaw gateway.
  • lib/public: Setup UI frontend (component-driven tabs and flows for providers, envars, watchdog, webhooks, and onboarding).
  • lib/setup: Prompt hardening templates and setup-related assets injected into agent/system behavior.

Runtime model:

  1. AlphaClaw server starts and manages OpenClaw as a child process.
  2. Setup UI calls AlphaClaw APIs for configuration and operations.
  3. AlphaClaw proxies gateway traffic and handles watchdog monitoring/repair.

Key Technologies

  • Node.js 22.22.3+ runtime (or a supported Node 24.15+/25.9+ release).
  • Express-based HTTP API server.
  • http-proxy for gateway proxy behavior.
  • OpenClaw CLI/gateway process orchestration.
  • Preact + htm frontend patterns for Setup UI components.
  • Vitest + Supertest for server and route testing.

Coding Conventions

Change Patterns

  • Keep edits targeted and production-safe; favor small, reviewable changes.
  • Preserve existing behavior unless the task explicitly requires behavior changes.
  • Follow existing UI conventions and shared components for consistency.
  • Reuse existing server route and state patterns before introducing new abstractions.
  • Update tests when behavior changes in routes, watchdog flows, or setup state.
  • Before running tests in a fresh checkout, run npm install so vitest (devDependency) is available for npm test.

Read the full file on GitHub · 236 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. 3d ago First seen · 236 lines · 3,891 tokens per session scan A b4fdcdb78855

Subscribe to this mod's changes

alphaclaw AGENTS.md is an instructions file published in the GitHub repository chrysb/alphaclaw (1,470 stars, last pushed 3d ago), licensed MIT. It adds 3,891 tokens to every session, about $0.0195 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.

Building agentsai-agentgatewaynodejsopenclawsetup-uiwatchdog
Related

Other instructions, from other repositories

hotplex AGENTS.md

Instructions for hrygo/hotplex, covering hotplex 项目知识库, 约定与规范, 必须遵守, 反模式（禁止） and 代码编辑规则.

hrygo/hotplex · 4,583 tokens

FlowBoard AGENTS.md

Instructions for rasimme/FlowBoard, covering flowboard — agent entry point, start here and where things live.

rasimme/FlowBoard · 450 tokens

hotplex CLAUDE.md

Instructions for hrygo/hotplex, a project described as: HotPlex — Unified access layer for AI Coding Agent.

hrygo/hotplex · 3 tokens

librefang AGENTS.md

Instructions for librefang/librefang, covering stack, layout, build, architecture and kernelhandle trait.

librefang/librefang · 2,087 tokens

openclaw CLAUDE.md

Claude Code instructions for openclaw/openclaw, a project described as: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞.

openclaw/openclaw · 3 tokens

aisix CLAUDE.md

Instructions for api7/aisix, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

api7/aisix · 7,972 tokens