Skip to main content
ClaudeWave

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。

Skills3.8k stars112 forksTypeScriptMITUpdated yesterday
ClaudeWave Trust Score
92/100
Verified
Passed
  • Open-source license (MIT)
  • Actively maintained (<30d)
  • Clear description
  • Topics declared
Last scanned: 9/3/2026
Install as a Claude Code skill
Method: Clone
Terminal
git clone https://github.com/liustack/modlens ~/.claude/skills/modlens
1. Clone the repository into your ~/.claude/skills directory (or copy the skill folder containing SKILL.md).
2. Start a new Claude Code session so the skill registry reloads.
3. Invoke it by name, or let Claude trigger it automatically when the task matches.
💡 If the repo bundles several skills, copy only the folders you need.

1 items in this repository

modlensSkill

Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI).

Install
Use cases

Skills overview

README preview not available. Visit the repo on GitHub for full documentation.
agent-skillsclaude-codeclaude-skillscodexcordisdeepseekdshdsh-pluginglmharnessharness-engineeringhermes-agentimage-to-textmultimodalocropenclawpi-agenttext-only-llmvisionvision-transformer

What people ask about modlens

What is liustack/modlens?

+

liustack/modlens is skills for the Claude AI ecosystem. The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。 It has 3.8k GitHub stars and its last recorded update is dated 2026-09-01.

How do I install modlens?

+

You can install modlens by cloning the repository (https://github.com/liustack/modlens) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is liustack/modlens safe to use?

+

Our security agent has analyzed liustack/modlens and assigned a Trust Score of 92/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains liustack/modlens?

+

liustack/modlens is maintained by liustack. The last recorded GitHub activity is dated 2026-09-01, with 5 open issues.

Are there alternatives to modlens?

+

Yes. On ClaudeWave you can browse similar skills at /categories/skills, sorted by popularity or recent activity.

Deploy modlens to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: liustack/modlens
[![Featured on ClaudeWave](https://claudewave.com/api/badge/liustack-modlens)](https://claudewave.com/repo/liustack-modlens)
<a href="https://claudewave.com/repo/liustack-modlens"><img src="https://claudewave.com/api/badge/liustack-modlens" alt="Featured on ClaudeWave: liustack/modlens" width="320" height="64" /></a>

More Skills

farion1231
cc-switch
today

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

130.8k9kRust
Skillsai-toolsclaude-codeInstall
Egonex-AI
Understand-Anything
today

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

81.3k6.8kTypeScript
Skillsantigravity-skillsbusiness-knowledgeInstall
code-yeongyu
oh-my-openagent
today

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

68.6k5.6kTypeScript
Skillsaiai-agentsInstall
tt-a1i
archify
yesterday

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

44.1k2.8kJavaScript
Skillsagent-skillsarchitecture-as-codeInstall
K-Dense-AI
scientific-agent-skills
today

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

42.1k3.9kPython
Skillsagent-skillsai-scientistInstall
VoltAgent
awesome-agent-skills
today

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

33.6k3.6k
Skillsagent-skillsai-agentsInstall