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 HistOracle-production/blabberer --skill lip-sync-pipelinegit clone --depth 1 https://github.com/HistOracle-production/blabbererWrote 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/historacle-production/blabberer/lip-sync-pipeline)<a href="https://agentmods.dev/skills/historacle-production/blabberer/lip-sync-pipeline"><img src="https://agentmods.dev/badge/skills/historacle-production/blabberer/lip-sync-pipeline/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/historacle-production/blabberer/lip-sync-pipeline"><img src="https://agentmods.dev/badge/skills/historacle-production/blabberer/lip-sync-pipeline.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 | $0.00068 | $0.01334 |
| Opus 5 | $0.00034 | $0.00667 |
| Sonnet 5 | $0.00014 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
lip-sync-pipeline 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blabberer — Lip Sync Sprite Pipeline
Generate 9 mouth shape sprites from any face image using AI.
Input Image → Face Detection → Gemini AI → 9 Mouth Shapes → Background Removal → Soft Edges → Ready
Installation
If you don't already have the blabberer Python package installed:
# Clone the repo (if not already cloned)
git clone https://github.com/HistOracle-production/blabberer.git
cd blabberer
# Install the Python package
pip install -e .
# OR
uv pip install -e .
Set your OpenRouter API key:
export OPENROUTER_API_KEY=sk-or-... # Get one at https://openrouter.ai/keys
First run downloads the rembg U2Net model (~170MB). Subsequent runs are instant.
Quick Pipeline
One-command generation
blabberer generate <image_path> --output-dir ./sprites --verbose
This auto-detects the face, generates all 9 shapes, removes backgrounds, and applies soft edges.
Output:
sprites/
├── shape_A.png through shape_H.png, shape_X.png # Raw PNGs
├── shape_A.webp through shape_X.webp # Transparent background
└── soft/
└── shape_A.webp through shape_X.webp # Production-ready (soft edges)
Manual face crop (if auto-detection fails)
blabberer generate image.png --crop-box left,top,right,bottom
The 9 Preston Blair Shapes
| Shape | Phonemes | Mouth Position |
|---|---|---|
| A | M, B, P | Lips pressed together |
| B | S, T, D, K, N | Slightly parted, teeth visible |
| C | A, I | Open mouth (speaking vowels) |
| D | E | Wide horizontal stretch |
| E | O | Rounded oval |
| F | U, W, Q | Puckered lips |
| G | F, V | Upper teeth on lower lip |
| H | L, T, D, N | Barely parted |
| X | (idle) | Resting/closed mouth |
Running the Demo
The repo includes a browser-based demo that plays audio with real-time lip sync:
cd demo
npm install
npm run dev
# Opens http://localhost:5173
Demo modes
Canvas mode (simple.html — default): Draws mouth shapes on a canvas overlay. Works immediately, no sprites needed.
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.
- 10d ago First seen · 167 lines · 68 tokens per session scan A 3c828135070f
lip-sync-pipeline is a skill published in the GitHub repository HistOracle-production/blabberer (3 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 1,334 once invoked, about $0.0003 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.
Other skills, from other repositories
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
generate-motion
Use when the user needs an animation clip on a rigged character — idle/walk/run/attack from the curated Meshy library. Picks the right curated motion, attaches the resulting clip to an AnimationPlayer. Trigger on "animation", "animate", "idle", "walk", "run", "attack animation", "motion", "mocap", "dance", "death…
auto-rig
Make a 3D model animation-ready — add a humanoid skeleton and skin weights to an existing GLB, or generate a rigged avatar from text/images in one call. Use when you or the user want to rig a mesh, auto-rig a GLB, make a model animatable, get a character that plays idle/walk animations, or go from prompt straight to a…
pipeline-automation
Automate 3D asset pipelines, including batch optimization, material baking, and exports for platforms like Unity and VRChat.
motiscope-recreate
Recreate an analyzed animation as working web code — GSAP (JavaScript), CSS/Web Animations, Framer Motion (React), or Lottie/SVG. Use after motiscope-analyze, or when the user asks to "build/recreate this animation in ". Reads the motiscope animation spec and emits a runnable component.
meshy-3d-generation
Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…