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/sharpai/deepcamera/sam2-segmentationnpx skills add SharpAI/DeepCamera --skill sam2-segmentationgit clone --depth 1 https://github.com/SharpAI/DeepCameraWhat 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 | $0.00023 | $0.00680 |
| Opus 5 | $0.00012 | $0.00340 |
| Sonnet 5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
segmentation-sam2 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 yesterday.
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.
What it actually says
SAM2 Interactive Segmentation
Click anywhere on a video frame to segment objects using Meta's Segment Anything 2. Generates pixel-perfect masks for annotation, tracking, and dataset creation.
What You Get
- Click-to-segment — click on any object to get its mask
- Point & box prompts — positive/negative points and bounding box selection
- Video tracking — segment in one frame, propagate across the clip
- Annotation Studio — full integration with sidebar Annotation Studio
Protocol
Communicates via JSON lines over stdin/stdout.
Aegis → Skill (stdin)
{"event": "frame", "frame_path": "/tmp/frame.jpg", "frame_id": "frame_1", "request_id": "req_001"}
{"command": "segment", "points": [{"x": 450, "y": 320, "label": 1}], "request_id": "req_002"}
{"command": "track", "frame_path": "/tmp/frame2.jpg", "frame_id": "frame_2", "request_id": "req_003"}
{"command": "stop"}
Skill → Aegis (stdout)
{"event": "segmentation", "type": "ready", "request_id": "", "data": {"model": "sam2-small", "device": "mps"}}
{"event": "segmentation", "type": "encoded", "request_id": "req_001", "data": {"frame_id": "frame_1", "width": 1920, "height": 1080}}
{"event": "segmentation", "type": "segmented", "request_id": "req_002", "data": {"mask_path": "/tmp/mask.png", "mask_b64": "...", "score": 0.95, "bbox": [100, 50, 350, 420]}}
{"event": "segmentation", "type": "tracked", "request_id": "req_003", "data": {"frame_id": "frame_2", "mask_path": "/tmp/track.png", "score": 0.93}}
Installation
The deploy.sh bootstrapper handles everything — Python environment, GPU detection, dependency installation, and model download. No manual setup required.
./deploy.sh
What ships with it
4 files 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.
- yesterday First seen · 68 lines · 23 tokens per session scan A 09c85923eeec
segmentation-sam2 is a skill published in the GitHub repository SharpAI/DeepCamera (3,025 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 680 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
addressing-pr-review-comments
Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review comments and general PR (issue) comments. Use when a PR has reviewer feedback to address, including code changes, style fixes, and documentation updates.
generating-changelog
Generates polished website release notes between two git tags for docs.streamlit.io. Use when preparing a new Streamlit release or reviewing changes between versions.
understanding-streamlit-architecture
Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun…
fixing-flaky-e2e-tests
Diagnose and fix flaky Playwright e2e tests. Use when tests fail intermittently, show timeout errors, have snapshot mismatches, or exhibit browser-specific failures.
fixing-streamlit-ci
Analyze and fix failed GitHub Actions CI jobs for the current branch/PR. Use when CI checks fail, PR checks show failures, or you need to diagnose lint/type/test errors and verify fixes locally.
implementing-feature
Implement a feature from a product/tech spec, URL, GitHub issue, or by auto-selecting the next papercut enhancement. Reads the spec, implements the feature following Streamlit patterns, and creates a merge-ready PR. Use when given a spec folder path, document URL, or issue link to implement, or when asked to implement…