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 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/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/desy-design/ag3nt/camera-capture"><img src="https://agentmods.dev/badge/skills/desy-design/ag3nt/camera-capture.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 | $0.00021 | $0.00445 |
| Opus 5.5 | $0.00008 | $0.00178 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 8d ago), licensed MIT. It adds 21 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5.5. 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.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.