Samples tested
0
across 7 categories
Honest Token Study
Demo compares baseline prose, caveman mode, and stenographer mode across 50+ samples in 7 categories.
Includes failure cases where steno underperforms. Token counts via gpt-tokenizer.
Primary command: /steno
Samples tested
0
across 7 categories
Caveman reduction
0%
vs baseline
Steno reduction
0%
vs baseline
Steno beats caveman
0%
of samples
Category Breakdown
Release Channel
preview
Productized bundle with install and export flow.
Platforms
0
Current starter-pack coverage.
Bundle Status
ready
Installer, prompt, skill, demo, packs.
Install Surface
Run npx --yes github:AkashAi7/stenographer-mode install --scope user for a user-wide install, or switch to --scope project for .github/prompts.
Use /steno in prompt picker or trigger it with “steno mode” phrasing. For context conversion, use /steno-compress temporary or /steno-compress permanent.
Install the CLI globally with npm install -g github:AkashAi7/stenographer-mode, or run install/export-pack.ps1 to generate a shareable distribution bundle.
How it works
Remove filler, social framing, and repeated setup.
Swap repeated concepts to stable abbreviations like cfg, deps, and ctx.
Use symbols like ->, w/, and vs to compress relations.
Leave commands, code, paths, exact errors, versions, and identifiers untouched.
Mode Comparison
Infographic
Exact benchmark via gpt-tokenizer. Artifact: benchmarks/latest.json.
Distribution
VS Code skill, VS Code user prompt, local caveman comparator, installer scripts, static demo, product manifest, Claude pack, Cursor pack, ChatGPT pack.
Same concept, multiple platform-native wrappers. Each platform gets its own instruction surface and trigger syntax.
Create platform packs for Claude, Cursor, ChatGPT, and web docs so activation feels native everywhere.
Release Kit
install/install.ps1
bundle.json
release.json
bundles/vscode/steno.prompt.md