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 agentmods add skills/desy-design/ag3nt/camera-capturenpx skills add desy-design/AG3NT --skill camera-capturegit clone --depth 1 https://github.com/desy-design/AG3NTWrote 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/desy-design/ag3nt/camera-capture)<a href="https://agentmods.dev/skills/desy-design/ag3nt/camera-capture"><img src="https://agentmods.dev/badge/skills/desy-design/ag3nt/camera-capture.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00445 |
| Opus 5 | $0.00010 | $0.00222 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
camera-capture 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 5d 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.
This is a copy
100% identical to camera-capture — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Camera Capture Skill
⚠️ Stub Skill: This is a placeholder for future camera functionality.
Current Status
Camera capture is not available on this device/node. This skill is a stub marking a future expansion point for the multi-node architecture.
When Camera Will Be Supported
Camera functionality will be implemented when:
- A companion node with camera capability is connected
- The user explicitly grants camera permissions
- The device has an accessible camera API
Planned Features
Capture Image
Capture a single image from the default camera.
Not implemented - returns "Camera not available on this device"
List Cameras
List available camera devices.
Not implemented - returns "Camera not available on this device"
Multi-Node Architecture
In the future, camera requests can be routed to a companion node (e.g., a phone or Raspberry Pi with camera) using the node_capability: camera metadata.
Example routing flow:
- User says "take a photo"
- Gateway checks for nodes with
cameracapability - If found, routes request to that node
- Node captures image and returns it
Notes
- Camera access requires user consent
- Images should be stored with proper privacy controls
- Consider thumbnail generation for previews
- Support for both front and back cameras (on mobile devices)
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.
- 5d ago First seen · 78 lines · 21 tokens per session scan A 35321412aa67
camera-capture is a skill published in the GitHub repository desy-design/AG3NT (2 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to camera-capture, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
camera-capture
Capture images from device camera. Currently a placeholder - camera support depends on device capabilities.
app-launcher
Launch applications, open URLs in browser, and list running processes. Requires approval for launching applications.
file-manager
Open files with default applications, reveal files in explorer/finder, and search for files on the system. Requires approval for operations outside workspace.
system-info
Get system information including CPU usage, memory, disk space, battery status, and network info. Read-only and safe to use.
voice-tts
Text-to-speech output for voice responses. Uses pyttsx3 for local TTS on supported systems.
fleetq-connect
Connect an agent to FleetQ over MCP or the REST API, including obtaining credentials via dynamic client registration.