agentmods.dev

vision-tool

vision-tool is a skill for Claude Code, Codex from farhanic017/vision-tool. It costs 57 tokens per session (2,174 once invoked), scanned C, original, GPL-3.0.

An image and video analysis tool for coding assistants, including assistants whose underlying model cannot interpret visual files directly.

In plain words
What is it for?
Use it when a coding task involves inspecting image or video files.
Why use it?
It lets the assistant work with visual files instead of refusing them or relying only on filenames and text descriptions.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

not rated 17repo 25d ago C scan 57 tokens GPL-3.0

Good fit Use it when a coding task involves inspecting image or video files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/farhanic017/vision-tool/vision-tool
View source ↗ farhanic017/vision-tool
Install

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.

Any agent
npx skills add farhanic017/vision-tool --skill vision-tool
Clone the repo
git clone --depth 1 https://github.com/farhanic017/vision-tool

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vision-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/farhanic017/vision-tool/vision-tool/github.svg)](https://agentmods.dev/skills/farhanic017/vision-tool/vision-tool)
Your own site
<a href="https://agentmods.dev/skills/farhanic017/vision-tool/vision-tool"><img src="https://agentmods.dev/badge/skills/farhanic017/vision-tool/vision-tool/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vision-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/farhanic017/vision-tool/vision-tool"><img src="https://agentmods.dev/badge/skills/farhanic017/vision-tool/vision-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02174
Opus 5.5 $0.00023 $0.00870
Sonnet 5.5 $0.00011 $0.00435
Haiku 4.5 $0.00006 $0.00217

Measured 2mo ago against content hash 718ad29ec124, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

vision-tool scanned grade C with 1 finding 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 2mo 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

Never refuse, never say "I can't view images".
SKILL.md · 241 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

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.

  1. 2mo ago First seen · 241 lines · 57 tokens per session scan C 718ad29ec124

Subscribe to this mod's changes

vision-tool is a skill published in the GitHub repository farhanic017/vision-tool (17 stars, last pushed 25d ago), licensed GPL-3.0. It adds 57 tokens to every session and 2,174 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeCreative and mediaai-agentai-agentsclaude-desktopcomputer-visioncontinue-dev
Related

vision-tool compared with skills from other repositories

vision-tool next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vision-toolfarhanic017/vision-toolSkill1725d agoGPL-3.0C57Claude Code, Codex
skill-release-gaterohitg00/ai-engineering-from-scratchSkill77ktodayMITA36Claude Code, Codex
orchard-releaserohitg00/ai-engineering-from-scratchSkill77ktodayMITA11Claude Code, Codex
orchard-reviewrohitg00/ai-engineering-from-scratchSkill77ktodayMITA8Claude Code, Codex
liveagent-code-reviewStack-Cairn/LiveAgentSkill2.3kyesterdayMITA54Claude Code, Codex
bdd-container-updateNVIDIA-AI-Blueprints/video-search-and-summarizationSkill2.0kyesterdayApache-2.0A117Cursor
tool-foundation-sprint-founding-hypothesisproduct-on-purpose/pm-skillsSkill7883d agoApache-2.0A109Claude Code