No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by liustack · Claude Skill · ★ 415
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is modsearch safe to install? View the security audit →
ModSearch A search plugin for OpenClaw, Claude Code, and other AI coding agents — turns search queries into structured web evidence, bridging the search gap for LLM workflows. 中文说明 Features Built for agent workflows that need reliable external search context Provider-extensible architecture (ships with as default provider) Outputs machine-consumable JSON (, , ) Designed to be called from Agent Skills (OpenClaw, Claude Code, Codex, Cursor, etc.) Single responsibility: search only (no image parsing, no page fetching) Install Or run with : Or install as an Agent Skill — tell any AI coding tool that supports agent skills (Claude Code, Codex, OpenCode, OpenClaw, Cursor, Antigravity, etc.): Or use the CLI directly: If you use the default provider, install and authenticate Gemini CLI first: Usage bash Print JSON result to stdout modsearch -q "OpenAI latest news" Save to file modsearch -q "OpenAI latest news" -o search.json Select provider + model and control result count modsearch -q "TypeScript 5.9 release notes" -p gemini-cli -m gemini-2.5-flash --max-results 6
| Stars | 415 |
| Forks | 14 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 73.7748894863197/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-07 |
| Created | 2026-02-22 |
| Platforms | browser, claude-code, codex, node |
| Est. Tokens | ~14k |
Looking for a modsearch alternative? If you're comparing modsearch with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Local-first desktop widget for tracking token usage, costs, and limits across 35+ AI coding tools—including Cl
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and cus
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agent
BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup wi
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across lo
Explore other popular claude skill tools:
modsearch is 🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON eviden. It is categorized as a Claude Skill with 415 GitHub stars.
modsearch is primarily written in TypeScript. It covers topics such as agent-skills, agentic-workflow, claude-code.
You can find installation instructions and usage details in the modsearch GitHub repository at github.com/liustack/modsearch. The project has 415 stars and 14 forks, indicating an active community.
modsearch is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to modsearch on Agent Skills Hub include token-monitor, wesight, graph-memory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: