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.
npx skills add KuaaMU/mcp-vision-bridge --skill visiongit clone --depth 1 https://github.com/KuaaMU/mcp-vision-bridgeWrote 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.
[](https://agentmods.dev/skills/kuaamu/mcp-vision-bridge/vision)<a href="https://agentmods.dev/skills/kuaamu/mcp-vision-bridge/vision"><img src="https://agentmods.dev/badge/skills/kuaamu/mcp-vision-bridge/vision/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.
<a href="https://agentmods.dev/skills/kuaamu/mcp-vision-bridge/vision"><img src="https://agentmods.dev/badge/skills/kuaamu/mcp-vision-bridge/vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00132 | $0.03310 |
| Opus 5 | $0.00066 | $0.01655 |
| Sonnet 5 | $0.00026 | $0.00662 |
| Haiku 4.5 | $0.00013 | $0.00331 |
Grade B, and why
vision scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Codex** — `~/.codex/config.toml`: How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision for a text-only agent
Your model cannot receive image content directly. When the user pastes an image,
Claude Code shows it as an [Unsupported Image] placeholder — a text marker with
no usable pixel data. You cannot read it. Instead, obtain the image through a
route you can access, then send it through the analyze_image MCP tool, which
forwards the pixels to a multimodal model and returns a detailed text description.
This skill has two parts:
- A. Install — if
analyze_imageis not available, get it configured. - B. Use — how to route any image through
analyze_image.
A. Install (run only if analyze_image is missing)
First check: is analyze_image available? If you can see analyze_image among
your MCP tools, skip to B. If it is NOT in your tool list, the vision MCP is
not configured yet. Do the following.
A1. Fast path — one-click installer (recommended):
If the repo is available on the machine, tell the user to run:
cd mcp-vision-bridge # wherever the repo is cloned
./install.sh
The installer will:
- Detect the agent platform (Claude Code / Codex / opencode / Kimi Code / Cowork).
- Prompt for the vision model endpoint, API key, and model name.
- Write the API key into the MCP server config env (NOT into shell profiles).
- Write the MCP server config into the platform's config file.
- Copy this skill into place.
- Optionally install the auto-loop hook (Claude Code): a UserPromptSubmit
hook that detects when the user pasted images and tells you to analyze them
with
image="session"— no snapshot, no lag, all pasted images in one call. No clipboard dependency. - Optionally register the MCP server into Cowork (Claude-3p desktop), which saves pasted images to files automatically and needs no hook.
- Print "restart your agent" instructions.
If a
[vision-bridge]system message appears in your context, that's the auto-loop hook firing: the user pasted images and wants you to look at them. Follow it — callanalyze_image(image="session", ...)to analyze them all.
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.
- 10d ago First seen · 246 lines · 132 tokens per session scan B fa428363ea75
vision is a skill published in the GitHub repository KuaaMU/mcp-vision-bridge (12 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 3,310 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
image-context-runtime
Use for image-heavy Codex work when generated or inspected media should stay behind a bounded MCP boundary and the controlling task should receive only durable Job IDs, hashes, relative references, and compact text handoffs.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.