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 idea2realClaw/myAgent --skill mac-cameragit clone --depth 1 https://github.com/idea2realClaw/myAgentWrote 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/idea2realclaw/myagent/mac-camera)<a href="https://agentmods.dev/skills/idea2realclaw/myagent/mac-camera"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/mac-camera/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/idea2realclaw/myagent/mac-camera"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/mac-camera.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 | $0.00082 | $0.00610 |
| Opus 5.5 | $0.00033 | $0.00244 |
| Sonnet 5.5 | $0.00016 | $0.00122 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
mac-camera 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mac Webcam Photo Taker
Use Mac's built-in webcam to take photos and display them directly in the conversation.
Core Script
python3 ~/.workbuddy/skills/mac-camera/scripts/mac_camera.py [--output <path>] [--http-share]
Workflow
- Open Photo Booth: Kill existing instance, then launch fresh
- Get window geometry via AppleScript (
System Events) - Screenshot the Photo Booth window using
screencapture -R - Crop the webcam preview area (remove title bar, filmstrip, controls) using PIL
- Share via HTTP (optional
--http-share) — startspython3 -m http.server 3000on/tmpif not running
Delivering Photos to the User
Use preview_url tool, NOT deliver_attachments for displaying images:
preview_url(url="http://localhost:3000/mac_camera_photo.png")
Steps:
- Run script with
--http-shareto get the URL - Parse the JSON output, extract
preview_url - Call
preview_url(url)with that URL
If --http-share was not used, first copy the photo to a shared directory and start HTTP server:
cp /tmp/mac_camera_photo.png /tmp/shared_photo.png
# ensure HTTP server running at port 3000 on /tmp
preview_url(url="http://localhost:3000/shared_photo.png")
Notes
- Requires Photo Booth app to be available (built-in on macOS)
- Photo Booth must be in foreground for the screenshot to capture the camera feed
- If the camera preview is black, the app may need to be brought to front or the camera may be in use by another app
- The HTTP server on port 3000 serves files from
/tmp; other agents should also have this running or copy files to their own shared directory - PIL (Pillow) is optional — if not available, the raw window screenshot is returned
Examples
# Take photo and print JSON result
python3 ~/.workbuddy/skills/mac-camera/scripts/mac_camera.py
# Save to specific path
python3 ~/.workbuddy/skills/mac-camera/scripts/mac_camera.py -o /tmp/my_photo.png
# Take photo and start HTTP server for sharing
python3 ~/.workbuddy/skills/mac-camera/scripts/mac_camera.py --http-share
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 First seen · 64 lines · 82 tokens per session scan A 5a14639c2836
mac-camera is a skill published in the GitHub repository idea2realClaw/myAgent (2 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 610 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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.