AlphaClaw is a browser-based management layer for OpenClaw, an AI-agent gateway, that guides setup and monitors running agents. It helps users configure multiple agents, manage integrations, recover gateway failures, and observe activity from one dashboard.
Borrowing it
Nothing to install: this file belongs to chrysb/alphaclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrysb/alphaclaw/main/AGENTS.mdgit clone --depth 1 https://github.com/chrysb/alphaclawWrote 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.
[](https://agentmods.dev/instructions/chrysb/alphaclaw/agents-md)<a href="https://agentmods.dev/instructions/chrysb/alphaclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/chrysb/alphaclaw/agents-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.
<a href="https://agentmods.dev/instructions/chrysb/alphaclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/chrysb/alphaclaw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03874 | $0.03874 |
| Opus 5.5 | $0.01550 | $0.01550 |
| Sonnet 5.5 | $0.00775 | $0.00775 |
| Haiku 4.5 | $0.00387 | $0.00387 |
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 1mo 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.
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:
- AlphaClaw server starts and manages OpenClaw as a child process.
- Setup UI calls AlphaClaw APIs for configuration and operations.
- AlphaClaw proxies gateway traffic and handles watchdog monitoring/repair.
Key Technologies
- Node.js 26.1+ runtime (or a supported Node 24.16+ release).
- Express-based HTTP API server.
http-proxyfor gateway proxy behavior.- OpenClaw CLI/gateway process orchestration.
- Preact +
htmfrontend 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 installsovitest(devDependency) is available fornpm test.
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.
- 1mo ago Changed · -17 tokens per session 98439e040e66
- 2mo ago First seen · 236 lines · 3,891 tokens per session scan A b4fdcdb78855
alphaclaw AGENTS.md is an instructions file published in the GitHub repository chrysb/alphaclaw (1,479 stars, last pushed 14d ago), licensed MIT. It adds 3,874 tokens to every session, about $0.0155 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 2026-08-30.
alphaclaw AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alphaclaw AGENTS.mdchrysb/alphaclaw | Instructions file | 1.5k | 14d ago | MIT | A | 3,874 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | 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 | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |