graphics-convert

graphics-convert is a command for coding agents from lesleslie/graphics-mcp. It costs 22 tokens per session (403 once invoked), scanned A, original, BSD-3-Clause.

An image-conversion command for changing a file into formats such as JPEG, PNG, GIF, BMP, WEBP, or TIFF.

In plain words
What is it for?
Use it to convert permitted image files, check their dimensions and metadata, choose a target format, and report the resulting file and size change.
Why use it?
It removes the need to use a separate image editor or remember format-specific conversion steps, while allowing quality and size optimization options.

Command

Part of the graphics plugin — 3 commands shipped together

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.

agentmods
npx agentmods add commands/lesleslie/graphics-mcp/graphics-convert
Clone the repo
git clone --depth 1 https://github.com/lesleslie/graphics-mcp

Or install graphics, the plugin that ships this one along with the rest of its 3 commands.

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 graphics-convert

README.md
[![agentmods](https://agentmods.dev/badge/commands/lesleslie/graphics-mcp/graphics-convert.svg)](https://agentmods.dev/commands/lesleslie/graphics-mcp/graphics-convert)
Your own site
<a href="https://agentmods.dev/commands/lesleslie/graphics-mcp/graphics-convert"><img src="https://agentmods.dev/badge/commands/lesleslie/graphics-mcp/graphics-convert.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00022 $0.00403
Opus 5 $0.00011 $0.00201
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 5d ago against content hash 783cc3f295d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graphics-convert scanned grade A with 0 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/graphics-convert.md · 33 lines

What it actually says

/graphics-convert

Convert an image to a different format using the graphics MCP server.

Usage

/graphics-convert <image-path> <target-format> [--quality N] [--optimize]

Arguments:

  • <image-path>: absolute path to the source image file. Must be under one of the directories returned by mcp__graphics__list_allowed_directories.
  • <target-format>: one of the formats returned by mcp__graphics__list_supported_formats (typically jpeg, png, gif, bmp, webp, tiff).
  • --quality N: optional, integer 1-100. Used for lossy targets (JPEG/WEBP).
  • --optimize: optional flag. Enables format-specific size optimization.

Workflow

  1. Call mcp__graphics__list_allowed_directories to confirm <image-path> is under a permitted root.
  2. Call mcp__graphics__list_supported_formats to validate the requested <target-format>.
  3. Call mcp__graphics__get_image_info with <image-path> to capture source dimensions and metadata for the report.
  4. Call mcp__graphics__convert_image with image_path, output_format, and any optional flags.
  5. Report the output path and the size delta (source bytes vs. converted bytes).

Example

/graphics-convert /Users/les/Pictures/photo.png webp --quality 85 --optimize

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. 5d ago First seen · 33 lines · 22 tokens per session scan A 783cc3f295d6

Subscribe to this mod's changes

graphics-convert is a command published in the GitHub repository lesleslie/graphics-mcp (1 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 22 tokens to every session and 403 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.