mediapipe-tracking

mediapipe-tracking is a skill for Claude Code, Codex from aeren23/image-processing-skills. It costs 31 tokens per session (1,424 once invoked), scanned A, original, MIT.

A guide to using Google MediaPipe, a computer-vision toolkit, to track faces, hands, and body positions in live video.

In plain words
What is it for?
Use it when building gesture controls, face filters, gaze or expression analysis, fitness apps, sign-language recognition, or virtual avatars.
Why use it?
It helps choose the right tracking method for the body parts and information needed, including depth and the number of people tracked. It also explains how MediaPipe compares with YOLO pose estimation, another computer-vision approach.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building gesture controls, face filters, gaze or expression analysis, fitness apps, sign-language recognition, or virtual avatars.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aeren23/image-processing-skills/07-mediapipe-tracking
Install

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.

Any agent
npx skills add aeren23/image-processing-skills --skill 07-mediapipe-tracking
Clone the repo
git clone --depth 1 https://github.com/aeren23/image-processing-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mediapipe-tracking

README.md
[![agentmods](https://agentmods.dev/badge/skills/aeren23/image-processing-skills/07-mediapipe-tracking/github.svg)](https://agentmods.dev/skills/aeren23/image-processing-skills/07-mediapipe-tracking)
Your own site
<a href="https://agentmods.dev/skills/aeren23/image-processing-skills/07-mediapipe-tracking"><img src="https://agentmods.dev/badge/skills/aeren23/image-processing-skills/07-mediapipe-tracking/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.

agentmods 80×15 button for mediapipe-tracking

Your own site · 80×15
<a href="https://agentmods.dev/skills/aeren23/image-processing-skills/07-mediapipe-tracking"><img src="https://agentmods.dev/badge/skills/aeren23/image-processing-skills/07-mediapipe-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.01424
Opus 5 $0.00015 $0.00712
Sonnet 5 $0.00006 $0.00285
Haiku 4.5 $0.00003 $0.00142

Measured 9d ago against content hash eed57d132e9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mediapipe-tracking 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 9d 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.

skills/07-mediapipe-tracking/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MediaPipe Tracking

When to Use This Skill

  • Tracking human body pose in real-time video
  • Detecting and tracking hand gestures or finger positions
  • Building face filters, expression analysis, or gaze tracking
  • Needing 3D depth information (Z-axis) for body landmarks
  • Creating fitness apps, sign language recognition, or virtual avatars

Decision Framework

Which MediaPipe Solution?

What body part do you need to track?
├── Full body pose (standing, sitting, exercising)
│   └── ✅ Pose Estimation — 33 landmarks, 3D (x, y, z)
│
├── Hands and fingers
│   └── ✅ Hand Tracking — 21 landmarks per hand
│
├── Face details (lips, eyes, eyebrows, jawline)
│   └── ✅ Face Mesh — 468 landmarks, 3D
│
└── Multiple tasks simultaneously
    └── ✅ Holistic — combines Pose + Hands + Face

MediaPipe vs YOLO Pose Estimation

Feature MediaPipe Pose YOLO Pose
Landmarks 33 (full body + face) 17 (body only)
Depth (Z-axis) ✅ Yes (camera-relative) ❌ No (2D only)
Speed ⚡ Very fast (optimized for mobile) ⚡ Fast
Multi-person ❌ Single person per frame ✅ Multiple people
3D Avatar ✅ Possible (Z depth) ❌ Not possible
Hand details ✅ 21 points per hand (separate solution) ❌ Not available
Face details ✅ 468 points (separate solution) ❌ Not available
Best for Single-user apps, gesture control, fitness Multi-person detection, surveillance

Rule of thumb: Need detailed single-person anatomy (hands, face, depth)? → MediaPipe. Need to detect multiple people quickly? → YOLO Pose.

Landmark Counts Reference

Solution Points Notable Landmarks
Pose 33 Nose, shoulders, elbows, wrists, hips, knees, ankles, eyes, ears
Hand 21 Wrist, thumb (4 joints), index (4), middle (4), ring (4), pinky (4)
Face Mesh 468 Lips contour, eye contour, eyebrows, nose bridge, jawline, iris

Read the full file on GitHub · 177 lines

Changes

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.

  1. 9d ago First seen · 177 lines · 31 tokens per session scan A eed57d132e9e

Subscribe to this mod's changes

mediapipe-tracking is a skill published in the GitHub repository aeren23/image-processing-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 1,424 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens