claude-skill

OmniGlyph

Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthropic/OpenAI/Gemini), fail-closed gates, measured benchmarks…
69 stars14 forksTypeScriptUpdated 8/3/2026100% free · open source
What it does

OmniGlyph reduces Claude bills by 59-70% by converting bulky LLM context into dense PNG pages with 100% read accuracy

When to use it
  • When you're using Claude for large-scale language model inference and want to minimize costs
  • When you need to optimize billing for multiple provider services like Anthropic, OpenAI, or Gemini
  • When you want to ensure fail-closed gates and measured benchmarks for your LLM workloads
Ready-to-paste prompt
Run the CLI command with a sample prompt to generate a dense PNG page, e.g., `node cli.js --prompt 'Your sample prompt here'`
Heads up: Ensure you have the required dependencies and a compatible TypeScript version installed, as OmniGlyph is built with TypeScript and may require specific runtime versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/omniglyph && curl -fsSL https://workflowstacks.com/api/skills/omniglyph/claude-skill -o ~/.claude/skills/omniglyph/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How OmniGlyph works
Codeflow
Free to inspect

OmniGlyph is a large TypeScript project (~28k lines across 64 code files, plus 82 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Large codebase
~28k lines · 64 code files · ~4 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
TypeScript 99%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/cli.js
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
  5. 5
    src/core/index.ts
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic83 files
bin/Command-line entry points1 files
docs/Documentation511 files
benchmarks/Evaluations & benchmarks28 files
eval/Evaluations & benchmarks13 files
scripts/Helper scripts5 files
config/Configuration1 files
tests/Tests — proof it works83 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
diegosouzapw
Language
TypeScript
Category
claude-skill
Published
7/6/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.