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-mediapipegit 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-mediapipe)<a href="https://agentmods.dev/skills/damionrashford/media-os/cv-mediapipe"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/cv-mediapipe/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-mediapipe"><img src="https://agentmods.dev/badge/skills/damionrashford/media-os/cv-mediapipe.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 | $0.00216 | $0.03719 |
| Opus 5 | $0.00108 | $0.01860 |
| Sonnet 5 | $0.00043 | $0.00744 |
| Haiku 4.5 | $0.00022 | $0.00372 |
Grade A, and why
cv-mediapipe 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 12d 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.
Solution: re-download with `curl -L`, verify file size matches upstream. How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cv-mediapipe
Context: $ARGUMENTS
Google MediaPipe Tasks API (mediapipe.tasks.python.*). Every Task in MediaPipe follows the same four-step shape: BaseOptions → <Task>Options → <Task>.create_from_options → detect/classify/recognize/generate. Docs home: https://ai.google.dev/edge/mediapipe/solutions/guide.
Critical gotcha — which MediaPipe?
MediaPipe has TWO Python APIs. Always use the new one.
| API | Status | Import |
|---|---|---|
mediapipe.solutions.* (legacy) |
DEPRECATED | from mediapipe.solutions import pose |
mediapipe.tasks.python.* (Tasks) |
CURRENT | from mediapipe.tasks.python import vision |
Never recommend the legacy solutions API for new work. The Tasks API has strictly more features (run modes, model hot-swap, explicit timestamps) and is the one Google ships updates for.
Quick start
- Face landmarks (478 points + blendshapes): → Step 3 (
mp.py face-landmark) - Hand landmarks (21 points / hand): → Step 3 (
mp.py hand-landmark) - Pose landmarks (33 points, 3D): → Step 3 (
mp.py pose-landmark) - Generic object detection: → Step 3 (
mp.py object-detect) - Selfie or interactive segmentation: → Step 3 (
mp.py segment) - Gesture classification: → Step 3 (
mp.py gesture) - Audio event classification: → Step 3 (
mp.py audio-classify) - Text classification / embedding / language-detect: → Step 3 (
mp.py text-*) - On-device LLM inference (Gemma / Phi-2): → Step 4 (
mp.py llm)
When to use
- Fast, portable, pre-trained vision models for faces, hands, bodies, gestures, segmentation — on CPU, no PyTorch/TF required.
- Mobile or embedded targets (Android, iOS, Raspberry Pi) — MediaPipe is the canonical Google stack there.
- Pair with
cv-opencvfor I/O + classical CV; MediaPipe hands you landmark/bbox tensors, OpenCV draws / saves / captures.
What ships with it
2 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.
- 12d ago First seen · 289 lines · 216 tokens per session scan A 39ea0c11e55a
cv-mediapipe is a skill published in the GitHub repository damionrashford/media-os (19 stars, last pushed 3mo ago), licensed MIT. It adds 216 tokens to every session and 3,719 once invoked, about $0.0011 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
moneyprinterturbo-video
Use this skill whenever the user wants to create a finished video from a topic, title, idea, prompt, or script with MoneyPrinterTurbo. This includes short-form, voice-over, educational, marketing, social-media, and stock-footage videos. Also use it when the user mentions MoneyPrinterTurbo, provides this Skill URL…
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…
prompt-engineering
ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices.
chief-data-officer
Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when…
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…