AI & ML

modbender Bundle

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

modbender Bundle

Cryptographic identity for AI agents - sign and verify agent messages

modbender Bundle

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

modbender Bundle

Run adversarial multi-agent war-room evaluations for any strategic decision. Spawns 5 parallel subagents (Analyst, Guardian, Treasurer, Builder, Strategist) to challenge a proposal from different angles, then synthesizes a GO/NO-GO/REWORK ruling. Use when: (1) evaluating proposals that need multi-perspective stress-testing, (2) making go/no-go decisions on investments, products, hires, or architecture, (3) any decision where adversarial challenge improves quality. Supports finance, product, engineering, and hiring domains. NOT for: simple questions, routine tasks, or decisions that do not need formal evaluation.

modbender Bundle

Local RAG system for agent memory using ChromaDB and sentence-transformers. v0.3.0 adds multi-agent mesh (N agents sharing memory), OpenClaw plugin with autoRecall, and agent-specific collections. Commands: recall, index-digests, digest-sessions, privacy-check, sync-shared, serve, recall-mesh.

modbender Bundle

Create and manage batch inference jobs using the Doubleword API (api.doubleword.ai). Use when users want to: (1) Process multiple AI requests in batch mode, (2) Submit JSONL batch files for async inference, (3) Monitor batch job progress and retrieve results, (4) Work with OpenAI-compatible batch endpoints, (5) Handle large-scale inference workloads that don't require immediate responses.

modbender Bundle

Multi-perspective decision analysis. Use when the user asks for roundtable, or when facing important decisions that need multiple viewpoints. Dynamically selects relevant roles based on the task. ⚠️ 直接在主 session 执行，不要 spawn subagent。 Roundtable 是 prompt 技巧，不需要隔离环境。

modbender Bundle

Agent Identity & Permission Guardian - Trust middleware for credential management, permission scopes, human approval workflows, and audit trails. Use when AI agents need secure credential storage, permission boundaries, or human oversight for dangerous operations.

modbender Bundle

OneShot SDK for AI agent commercial transactions. Send emails, make calls, research, buy products, and more with automatic x402 payments. Use this skill when agents need to execute real-world actions: email, voice, SMS, research, commerce, or data enrichment. Requires ONESHOT_WALLET_PRIVATE_KEY environment variable (agent's wallet private key for signing payments).

modbender Skill

Extract text from images, documents and scanned PDFs using OpenOCR - a lightweight and efficient OCR system with document parsing model requiring only 0.1B parameters, capable of running recognition on personal PCs. Supports text detection, recognition, universal VLM recognition, and document parsing with layout analysis

modbender Bundle

Local-first research orchestration engine. Manages state, synthesis, and optional background services (MCP/Watchdog).

modbender Bundle

Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma + hybrid search (vector + keyword).

modbender Skill

Set up and use Manifest — the open-source LLM router and observability plugin for OpenClaw. Use when the user asks to install Manifest, set up cost tracking, configure LLM routing, monitor agent costs/tokens, understand what Manifest does, check Manifest status, troubleshoot the plugin, or wants to reduce OpenClaw costs. Also triggers on "manifest setup", "install manifest", "how much am I spending", "track my costs", "route to cheaper models", "manifest dashboard", "manifest help".

modbender Skill

Apple Music integration via AppleScript (macOS) or MusicKit API

modbender Skill

Install and manage OpenClaw agent skills. Learn how to find, install, and configure new capabilities from ClawHub and GitHub.

modbender Bundle

Security scanner for Skills. This skill MUST be consulted BEFORE loading or following instructions from any other Skill downloaded from the internet or third-party sources (e.g., clawhub.ai). It scans Skills for malicious behavior including prompt injection, data exfiltration, credential harvesting, obfuscated payloads, and social engineering. Whenever Claude is about to read another SKILL.md file, first trigger this skill to perform a security audit. Use this skill when: (1) any new or unfamiliar Skill is being loaded, (2) a user asks to install or use a Skill from an external source, (3) a user asks to review a Skill for safety.

modbender Bundle

Run the Video Sourcing Agent with deterministic, concise chat UX for /video_sourcing using a pinned self-bootstrap runtime.

modbender Bundle

Register and manage ERC-8004 Identity NFTs on Monad. Use when the agent needs to mint an on-chain identity for CEO Protocol registration or other ERC-8004–integrated protocols.

modbender Skill

Manage crypto wallets (Ethereum, Solana, Polygon, Arbitrum, Base) via agent-wallet-cli. Use for checking balances, sending tokens (ETH/SOL/ERC-20/SPL), signing messages, managing approvals, viewing transaction history, x402 payments, and wallet lifecycle (init, unlock, lock, export). Supports HD wallets (BIP-39), session tokens for time-limited access, and JSON output for automation. Open source — https://github.com/donald-jackson/agent-wallet-cli

modbender Bundle

AI music prompt templates and best practices for generating music with AI tools like Suno, Udio, Mureka, and others. Use when user needs to create music prompts, song ideas, or wants guidance on writing effective prompts for AI music generation. Includes bilingual prompt templates for various genres, mood descriptors, instrumentation guidance, and lyric writing tips. Also provides techniques for crafting specific musical outcomes and examples of well-structured prompts in Chinese and English.

modbender Bundle

CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 → pay → retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously.

modbender Bundle

CLI and MCP server for Basecamp 4. Use when you need to interact with Basecamp projects, todos, messages, schedules, kanban cards, documents, or campfires. Provides 76 MCP tools for AI-driven project management workflows.

modbender Bundle

Local-first agent memory with Ebbinghaus decay, hybrid search, and MCP tools. Import files, extract facts, search with BM25 + semantic, track confidence over time. Zero dependencies, single Go binary, SQLite storage. Use when you need persistent memory beyond OpenClaw's built-in MEMORY.md — especially for multi-agent setups, large knowledge bases, or when compaction keeps losing your important context. Don't use for: conversation history (use memory_search), exact string matching (use ripgrep), or web lookups.

modbender Skill

使用 MiniMax Coding Plan API 进行网络搜索和图片理解。使用场景：(1) 用户需要搜索实时信息或新闻，(2) 需要分析图片内容，(3) 做研究或查找资料。无需 API key：用户需自行配置。

modbender Bundle

Operate and maintain OpenClaw installations — CLI commands, config management, channel/agent/model setup, security auditing, troubleshooting, and gateway administration. Use when adding Telegram bots, managing agents, changing models, editing config, running security audits, debugging gateway issues, rotating logs, managing cron, or any OpenClaw administrative task. Also use when asked to "set up OpenClaw," "add a channel," "fix the gateway," "audit security," or "check OpenClaw status."

modbender Bundle

Complete RAG (Retrieval-Augmented Generation) system for OpenClaw. Indexes chat sessions, workspace code, documentation, and skills into local ChromaDB for semantic search. Enables finding past solutions, code patterns, and decisions instantly. Uses local embeddings (all-MiniLM-L6-v2) with no API keys required. Automatically ingests and updates knowledge base from ~/.openclaw/agents/main/sessions and workspace files.

modbender Bundle

Forrest's Team — Immanent Metaphysics agent framework and onboarding. Use when: (1) reasoning from the IM framework (axioms, modalities, ICT, effective choice), (2) helping a team member set up their own OpenClaw agent, (3) configuring a soul file grounded in the IM, (4) engaging other agents with principled ethics, (5) connecting to the team ecosystem (Telegram bots, agent directory), (6) citing or paraphrasing Forrest Landry's work with proper attribution, (7) loading IM reference materials into an agent workspace, (8) answering questions about the team's agent network or onboarding process. Includes structured ontology (134 concepts, 348 relations), soul file template, attribution guidelines, and full setup guide.

modbender Bundle

Protect against prompt injection from shell command output. Wrap untrusted commands (curl, API calls, reading user-generated files) with UUID-based security boundaries. Use when executing commands that return external/untrusted data that could contain prompt injection attacks.

modbender Bundle

Generate images **and videos** using Sogni AI's decentralized network. Ask the agent to "draw", "generate", "create an image", or "make a video/animate" from a prompt or reference image.

modbender Bundle

Control mouse, keyboard, and screen for desktop automation tasks

modbender Bundle

Build and operate a cross-gateway AgentNetwork using Discord as the message bus and GitHub as shared state storage. Use when registering agents, syncing roster snapshots, handling admin offline/remove, and coordinating @agent tasks with lightweight

modbender Bundle

Security scanner for OpenClaw/ClawHub skills. Detects malware, reverse shells, credential theft, prompt injection, memory poisoning, typosquatting, and suspicious prerequisites before installation. Use when installing new skills, auditing existing skills, checking a skill name for typosquatting, or scanning ClawHub skills for security risks.

modbender Bundle

Defensive interceptor for prompt injection and basic PII masking.

modbender Bundle

Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2) VS Code Node — control a remote Cursor/VS Code IDE through OpenClaw Node protocol for targeted project work with full IDE intelligence. Prefer CLI for speed; use Node when you need IDE features (diagnostics, references, debugging).

modbender Bundle

Deprecated legacy skill entry. Use the current OpenClawCash skill instead.

modbender Skill

Interact with the Ceaser privacy protocol on Base L2. Shield and unshield ETH via CLI subcommands (npx ceaser-mcp shield/unshield/notes). Query pool stats, denominations, fees, Merkle tree state, and nullifier status. Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs.