Agent Skill

Modlens skill

modlensliustack/modlensskills/modlens/SKILL.md

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).

4.4kMIT

always on

240 tokname + description

once used

1,069 tokSKILL.md body

bundled files

72 scripts

repo stars

4.4kGitHub

Install the Modlens skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/liustack/modlens --skill modlens

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/liustack/modlens.git /tmp/modlens
mkdir -p ~/.claude/skills
cp -R /tmp/modlens/skills/modlens ~/.claude/skills/modlens

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	240 tok
When the agent uses it	The SKILL.md instructions	1,069 tok
Only if opened	7 bundled files (75 KB)	varies

Until it is used, modlens costs about 5.7× less than the median MCP server we measured (1,363 tokens on every turn). Skills vs MCP study

Checks

Ships scripts the agent can run. Read them before installing.

Pre-approved tools (allowed-tools): Bash. The agent can use these without asking while the skill is active.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

ModLens — Vision Bridge Skill
Run it
Ask the CLI, not this file
The loop
Failures