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 damionrashford/media-os --skill cv-opencvgit clone --depth 1 https://github.com/damionrashford/media-osWrote 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/damionrashford/media-os/cv-opencv)<a href="https://agentmods.dev/skills/damionrashford/media-os/cv-opencv"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/cv-opencv/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/damionrashford/media-os/cv-opencv"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/cv-opencv.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 | $0.00303 | $0.04172 |
| Opus 5 | $0.00151 | $0.02086 |
| Sonnet 5 | $0.00061 | $0.00834 |
| Haiku 4.5 | $0.00030 | $0.00417 |
Grade A, and why
cv-opencv scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L -o models/face_detection_yunet_2023mar.onnx \ How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cv-opencv
Context: $ARGUMENTS
OpenCV 4.x via the Python cv2 binding. Python is the first-class surface — the C++, Java (javadoc), and JS (opencv.js) APIs are parallel and the same concepts port over. Canonical docs: https://docs.opencv.org/4.x/.
Quick start
- Inspect an image (shape/dtype/channels): → Step 2 (
cv.py info) - Grab N frames from a webcam / file: → Step 3 (
cv.py capture) - Detect faces with the modern YuNet model: → Step 4 (
cv.py detect-faces) - Track a bounding box across frames: → Step 5 (
cv.py track) - Run an ONNX model via the dnn module: → Step 6 (
cv.py yolo) - Calibrate a camera from a chessboard: → Step 7 (
cv.py calibrate) - Stitch a panorama: → Step 8 (
cv.py stitch)
When to use
- User asks for face / object / landmark detection, optical flow, tracking, panorama, camera calibration, or any classical CV operation.
- Need to run an ONNX / TensorFlow / Caffe / Darknet model from Python without heavyweight frameworks (PyTorch, TF) —
cv2.dnnis the lightweight path. - Need to read/write video via FFmpeg, GStreamer, V4L2, AVFoundation, or MSMF with a uniform API (
cv2.VideoCapture/cv2.VideoWriter). - For pose/face landmark models trained by Google (MediaPipe Tasks), use the
cv-mediapipeskill instead — it's a different ecosystem with its own Tasks API.
Step 1 — Install the right OpenCV wheel
Three PyPI wheels, mutually exclusive — picking the wrong one hides features or wastes install.
| Wheel | Includes | Use when |
|---|---|---|
opencv-python |
main repo only | basic imgproc/videoio/dnn |
opencv-contrib-python |
main + contrib (ximgproc, tracking, aruco) | recommended default |
opencv-python-headless |
main, no GUI (no imshow) |
servers / Docker |
opencv-contrib-python-headless |
contrib, no GUI | headless + contrib modules |
What ships with it
3 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.
- 11d ago First seen · 287 lines · 303 tokens per session scan A 66e1bb641181
cv-opencv is a skill published in the GitHub repository damionrashford/media-os (18 stars, last pushed 3mo ago), licensed MIT. It adds 303 tokens to every session and 4,172 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
neo4j-driver-python-skill
Neo4j Python Driver v6 — driver lifecycle, executequery, managed and explicit transactions, async (AsyncGraphDatabase), result handling, data type mapping, error handling, UNWIND batching, connection pool tuning, and causal consistency. Use when writing Python code that connects to Neo4j via GraphDatabase.driver…