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 GOWTHAM2036/SightMCP --skill skillgit clone --depth 1 https://github.com/GOWTHAM2036/SightMCPWrote 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/gowtham2036/sightmcp/skill)<a href="https://agentmods.dev/skills/gowtham2036/sightmcp/skill"><img src="https://agentmods.dev/badge/skills/gowtham2036/sightmcp/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/gowtham2036/sightmcp/skill"><img src="https://agentmods.dev/badge/skills/gowtham2036/sightmcp/skill.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 | $0.00066 | $0.00870 |
| Opus 5.5 | $0.00026 | $0.00348 |
| Sonnet 5.5 | $0.00013 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
screen-aware 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen-Aware Development & Visual Targeting Skill
This skill teaches the agent how to leverage the Screen-Aware MCP tools to ground user intent in the current computer screen state, locate matching source components, apply modifications, and visually verify the results.
🧭 Core Principles & Rules of Engagement
-
Obtain Fresh Context for Visual References:
- Whenever the user refers to something visible on screen or uses deictic pointers ("this", "here", "that button", "the navbar icon"), call
capture_screen_context()immediately. - Never hallucinate or guess what is on the screen without capturing fresh screen context.
- Whenever the user refers to something visible on screen or uses deictic pointers ("this", "here", "that button", "the navbar icon"), call
-
Combine Screenshot and Cursor Coordinates:
- Use the mouse cursor coordinates
(x, y)and normalized coordinates(normalized_x, normalized_y)in tandem with the visual screenshot. - Reason about the specific UI element directly located under or nearest to the cursor position.
- Use the mouse cursor coordinates
-
Grounding to Source Code:
- After visually identifying the target element from the screenshot and active window:
- Note key semantic text, class names, icons, labels, or layout attributes visible in the element.
- Search the codebase for corresponding templates, components, JSX/TSX elements, or CSS rules.
- Ensure you have accurately located the component before modifying code.
- After visually identifying the target element from the screenshot and active window:
-
Visual Verification Loop:
- After applying code modifications and allowing the UI / hot-reload to refresh:
- Call
capture_screen_context()(orcapture_screen()) to capture an updated screen frame. - Visually verify that the requested visual changes (e.g., color, size, padding, alignment) have taken effect as requested.
- Report the verified outcome clearly to the user.
- Call
- After applying code modifications and allowing the UI / hot-reload to refresh:
-
Security & Privacy Guardrails:
- Never log or display sensitive personal information, credentials, or private message content captured in screenshots.
- Ask for user confirmation before executing any destructive operations.
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 First seen · 75 lines · 66 tokens per session scan A f34cf83b91be
screen-aware is a skill published in the GitHub repository GOWTHAM2036/SightMCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 870 once invoked, about $0.0003 per session on Opus 5.5. 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.
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…
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…