vision-upgrade

vision-upgrade is a skill for Claude Code from eralpozcan/vision-squeezer. It costs 93 tokens per session (1,905 once invoked), scanned C, original, no licence file.

An update task for VisionSqueezer that detects whether it was installed with Cargo, npm, or npx and runs the matching upgrade command.

In plain words
What is it for?
Use it when upgrading VisionSqueezer or when an npx cache or MCP registration is keeping the installation on an old release.
Why use it?
It handles installation-specific updates and clears the npx cache so an old cached package does not keep being used; it also re-registers the MCP server with a fixed version.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the vision-squeezer-mcp plugin — 3 skills, 1 MCP server shipped together

Good fit Use it when upgrading VisionSqueezer or when an npx cache or MCP registration is keeping the installation on an old release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eralpozcan/vision-squeezer/vision-upgrade
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 eralpozcan/vision-squeezer --skill vision-upgrade
Clone the repo
git clone --depth 1 https://github.com/eralpozcan/vision-squeezer

Made for: Claude Code.

Or install vision-squeezer-mcp, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/eralpozcan/vision-squeezer/vision-upgrade/github.svg)](https://agentmods.dev/skills/eralpozcan/vision-squeezer/vision-upgrade)
Your own site
<a href="https://agentmods.dev/skills/eralpozcan/vision-squeezer/vision-upgrade"><img src="https://agentmods.dev/badge/skills/eralpozcan/vision-squeezer/vision-upgrade/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-upgrade

Your own site · 80×15
<a href="https://agentmods.dev/skills/eralpozcan/vision-squeezer/vision-upgrade"><img src="https://agentmods.dev/badge/skills/eralpozcan/vision-squeezer/vision-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,905 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. 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 $0.00093 $0.01905
Opus 5 $0.00046 $0.00953
Sonnet 5 $0.00019 $0.00381
Haiku 4.5 $0.00009 $0.00191

Measured 10d ago against content hash c702dc93b390, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

vision-upgrade scanned grade C with 2 findings 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$HOME/.npm/_npx"

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

r = subprocess.run(['npx', '-y', f'vision-squeezer@{ver}'], input=req, capture_output=True, text=True, timeout=8, cwd=home)
plugins/vision-squeezer-mcp/skills/vision-upgrade/SKILL.md · 177 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

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. 10d ago First seen · 177 lines · 93 tokens per session scan C c702dc93b390

Subscribe to this mod's changes

vision-upgrade is a skill published in the GitHub repository eralpozcan/vision-squeezer (2 stars, last pushed 1mo ago), with no licence file. It adds 93 tokens to every session and 1,905 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.