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 RunhuaHuang/VisionPower --skill visionpower-skillgit clone --depth 1 https://github.com/RunhuaHuang/VisionPowerWrote 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/runhuahuang/visionpower/visionpower-skill)<a href="https://agentmods.dev/skills/runhuahuang/visionpower/visionpower-skill"><img src="https://agentmods.dev/badge/skills/runhuahuang/visionpower/visionpower-skill/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/runhuahuang/visionpower/visionpower-skill"><img src="https://agentmods.dev/badge/skills/runhuahuang/visionpower/visionpower-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 52 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 63 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 64 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 83 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Privilege Escalation · line 80 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00094 | $0.03220 |
| Opus 5.5 | $0.00038 | $0.01288 |
| Sonnet 5.5 | $0.00019 | $0.00644 |
| Haiku 4.5 | $0.00009 | $0.00322 |
Grade B, and why
visionpower 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.visionpower/config.json How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VisionPower
VisionPower is an image-understanding tool for non-multimodal (text-only) models. It sends one or more images to an external vision model for OCR, scene description, chart interpretation, or image comparison, and returns the results as text.
[!IMPORTANT] Models that can understand images directly must not call this skill. Use the model's own vision capability to read the image directly.
This skill is self-contained:
the script describe_image.mjs sits next to this file and runs with plain Node.js —
no npm install, no CLI to install, no extra dependencies. It only needs Node 18.14.1+
and a vision model API key.
Call the script by its absolute path. If this skill is installed at
~/.claude/skills/visionpower/, the script is
~/.claude/skills/visionpower/describe_image.mjs.
Response style (important)
Keep the mechanics invisible. The user wants the answer about their image, not a play-by-play of how you got it.
- Do not narrate or pre-check on normal calls. Do not run
node --version, do notcatthe config file, and do not announce "checking environment", "config exists", "running the script", etc. Just run the script once and answer. First-time setup is the only exception. - Run the script directly. Assume it is already set up. The script fails fast with a clear message if Node or the API key is missing — only THEN fall back to setup.
- Remember verified setup. The script writes a state marker at
~/.visionpower/skill-state.jsonafter any successful model call. If that marker says"configVerified": true, never do setup/config preflight on later calls; only ask the user to reconfigure if a later script run fails with a missing-key/auth/config error. - Do not expose internals in your reply: no command lines, no absolute paths, no raw request JSON, no model/config details. Present only the result (or a brief, plain-language error if it failed).
- Reply in the user's language, concise and direct — as if you simply looked at the image.
What ships with it
1 file 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.
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.
- 1mo ago Changed · +14 lines · -6 tokens per session a1c15eba39ab
- 1mo ago First seen · 220 lines · 100 tokens per session scan B 61ba18fb93de
visionpower is a skill published in the GitHub repository RunhuaHuang/VisionPower (68 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 3,220 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…