agentmods.dev

fastcar-vision-tools

fastcar-vision-tools is a skill for Claude Code, Codex from williamDazhangyu/-fastcar-mcp-vision-tools. It costs 139 tokens per session (1,871 once invoked), scanned C, original, MIT.

A command-line tool for configuring and operating FastCar Vision, an MCP server for image understanding and image generation. MCP is a standard way for an AI assistant to use external tools.

In plain words
What is it for?
Use it to inspect setup, repair agent registration, manage text and image model profiles, choose a default model, and configure image generation or editing providers.
Why use it?
It removes the need to construct configuration commands by hand and helps diagnose missing or incorrectly registered vision tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 18d ago C scan 139 tokens original MIT

Good fit Use it to inspect setup, repair agent registration, manage text and image model profiles, choose a default model, and configure image generation or editing providers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/williamdazhangyu/-fastcar-mcp-vision-tools/fastcar-vision-tools
View source ↗ williamDazhangyu/-fastcar-mcp-vision-tools
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 williamDazhangyu/-fastcar-mcp-vision-tools --skill fastcar-vision-tools
Clone the repo
git clone --depth 1 https://github.com/williamDazhangyu/-fastcar-mcp-vision-tools

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 fastcar-vision-tools

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/williamdazhangyu/-fastcar-mcp-vision-tools/fastcar-vision-tools"><img src="https://agentmods.dev/badge/skills/williamdazhangyu/-fastcar-mcp-vision-tools/fastcar-vision-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,871 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 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 5.1 $0.00139 $0.01871
Opus 5 $0.00069 $0.00936
Sonnet 5 $0.00028 $0.00374
Haiku 4.5 $0.00014 $0.00187

Measured 11d ago against content hash ab96092c2c1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

fastcar-vision-tools 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 11d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

- Add a model profile: run `mcp-vision-tools models add`. Let the secure prompt collect the API key.
skills/fastcar-vision-tools/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FastCar Vision Tools

Translate the user's natural-language request into the smallest deterministic mcp-vision-tools command sequence. Execute commands directly when the environment permits it; do not ask the user to reconstruct CLI arguments.

Route Intents

  • Inspect the installation or diagnose "MCP not found": run mcp-vision-tools doctor --agent --json, then repair the reported issue. Use mcp-vision-tools setup --agent --json when client registration is missing.
  • Configure interactively: run mcp-vision-tools config.
  • List model profiles: run mcp-vision-tools models list --agent --json.
  • Add a model profile: run mcp-vision-tools models add. Let the secure prompt collect the API key.
  • Edit a model profile: run mcp-vision-tools models edit <profile>. Let the secure prompt collect a replacement API key when needed.
  • Select the default model: run mcp-vision-tools models use <profile> --agent --json.
  • Remove a model profile: run mcp-vision-tools models remove <profile> --agent --json.
  • List image-generation profiles: run mcp-vision-tools image-models list --agent --json.
  • Add or edit an image profile: run mcp-vision-tools image-models add [name] or image-models edit [name]; let the secure prompt collect the API key and declared generate/edit capabilities.
  • Select per-operation defaults: run mcp-vision-tools image-models use <profile> generate|edit|both --agent --json.
  • Remove an image profile: run mcp-vision-tools image-models remove <profile> --agent --json.
  • Inspect managed image artifacts: run mcp-vision-tools artifacts status --agent --json. Add an explicit directory only when the user asks to inspect that directory.
  • Remove expired image artifacts: run mcp-vision-tools artifacts cleanup --agent --json. Use artifacts cleanup [directory] --all only after the user explicitly asks to delete every package-named artifact in that directory.
  • Replace-start or restart the background MCP service, validate the default model first, and automatically refresh client registrations: run mcp-vision-tools start|restart --agent --json. The safe default refuses to interrupt active tasks.
  • Start or restart only the daemon without changing client registrations: run mcp-vision-tools start|restart --daemon-only --agent --json. The same active-task guard applies.
  • Stop the background MCP service: run mcp-vision-tools stop --agent --json. Do not add --force unless the user explicitly authorizes interrupting the returned active tasks.
  • Check service state: run mcp-vision-tools status --agent --json.
  • Inspect service logs: run mcp-vision-tools logs.
  • Start stdio explicitly: run mcp-vision-tools stdio; reserve this for an MCP client process, not an interactive terminal session.
  • Check, repair, or remove this global Skill: run mcp-vision-tools skill status|sync|uninstall --agent --json. Explicit uninstall creates a persistent disabled marker, so CLI auto-repair does not reinstall it. An explicit skill sync removes that marker and enables the Skill again.
  • Analyze an image, screenshot, OCR target, or video from an Agent: ensure the MCP is configured and connected, then submit analyze_image or analyze_video, retain its taskId, and call wait_vision_task. Repeat that wait only when it returns waitTimedOut: true; use get_vision_task only for recovery or an immediate manual check. Use list_vision_models when profile selection is unclear.
  • Generate or edit images: call generate_image or edit_image only after the corresponding tool appears, then call wait_vision_task with the returned taskId until it reaches a terminal status. Omit outputDirectory for disposable results managed by the server's seven-day retention; pass an absolute workspace directory for durable deliverables because explicit directories are never auto-cleaned. Use list_image_models when profile selection is unclear.
  • Extend a nonstandard image provider: first decide whether changing Base URL/model is sufficient. If its wire protocol differs from OpenAI Images, read references/image-provider-adapter.md completely and implement a trusted external adapter module.

Read the full file on GitHub · 56 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 56 lines · 139 tokens per session scan C ab96092c2c1f

Subscribe to this mod's changes

fastcar-vision-tools is a skill published in the GitHub repository williamDazhangyu/-fastcar-mcp-vision-tools (0 stars, last pushed 18d ago), licensed MIT. It adds 139 tokens to every session and 1,871 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens