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.
npx skills add miketromba/skills --skill openclawgit clone --depth 1 https://github.com/miketromba/skillsWrote 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/skills/miketromba/skills/openclaw)<a href="https://agentmods.dev/skills/miketromba/skills/openclaw"><img src="https://agentmods.dev/badge/skills/miketromba/skills/openclaw.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.00937 |
| Opus 5 | $0.00050 | $0.00468 |
| Sonnet 5 | $0.00020 | $0.00187 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
openclaw 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 8d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw
OpenClaw is an open-source platform for deploying AI agents across multiple messaging channels.
Research Process
To answer questions about OpenClaw, spawn a sub-agent to conduct thorough documentation research.
Launch a Research Sub-Agent
Use the Task tool to spawn a sub-agent dedicated to OpenClaw documentation research. Do NOT specify a model (use the default model for comprehensive research quality).
Critical: Provide the sub-agent with a highly detailed prompt that includes:
- Goal - What you are ultimately trying to accomplish
- Context - Why you need this information and how it fits into the larger task
- Specific Questions - Exactly what information you need answered
- Output Requirements - The format and level of detail needed in the response
Task Tool Configuration
Task tool parameters:
- description: "Research OpenClaw docs"
- subagent_type: "generalPurpose"
- model: (DO NOT SPECIFY - use default for thorough research)
- readonly: true
- prompt: (see template below)
Prompt Template for Sub-Agent
Structure your prompt to the research sub-agent as follows:
You are researching OpenClaw documentation to help with a specific task.
## Your Research Goal
[Describe exactly what you need to accomplish with this information]
## Context
[Explain why you need this information and how it will be used]
## Specific Questions to Answer
[List the specific questions that need to be answered]
## Research Process
1. First, fetch the documentation index to see all available pages:
URL: https://docs.openclaw.ai/llms.txt
2. Based on the questions above, identify and fetch the most relevant documentation pages. The docs are organized by topic:
- automation/ - Cron jobs, webhooks, polling, auth monitoring
- channels/ - Messaging platform integrations (Slack, Discord, Telegram, WhatsApp, etc.)
- cli/ - Command-line interface commands
- concepts/ - Core concepts (agents, sessions, memory, context, models)
- gateway/ - Gateway configuration, sandboxing, authentication
- install/ - Installation guides (Docker, Bun, Nix, Ansible)
- platforms/ - Platform-specific guides (macOS, Linux, Windows, iOS, Android)
- providers/ - LLM provider integrations (Anthropic, OpenAI, OpenRouter)
- tools/ - Built-in tools (browser, exec, skills, subagents)
- start/ - Getting started guides
- reference/ - Templates and reference materials
3. Fetch multiple relevant pages in parallel using WebFetch.
## Required Output
[Specify exactly what format and content you need returned]
Provide a comprehensive response with all findings, including relevant code examples, configuration snippets, and step-by-step instructions where applicable.
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.
- 8d ago First seen · 113 lines · 100 tokens per session scan A 17b785dffe3e
openclaw is a skill published in the GitHub repository miketromba/skills (2 stars, last pushed 12d ago), licensed MIT. It adds 100 tokens to every session and 937 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…