A Claude Code skill that compresses AI agent output using the grammar of Newspeak from Orwell's 1984 to reduce token usage while preserving code, errors, and critical instructions.

Stars

32

7-day growth

No data

Forks

1

Open issues

0

License

NOASSERTION

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

Combines a literary parody with practical cost-saving; transparently discloses limitations and caveats; includes safety measures to never compress security warnings or destructive commands.

Who it is for

  • Claude Code users seeking to reduce token costs
  • Developers working with AI coding assistants
  • Teams using AI in CI/CD pipelines
  • Fans of George Orwell's 1984 looking for creative tech projects

Use cases

  • Reducing output token consumption during long AI-assisted coding sessions
  • Compressing verbose AI chat commentary while keeping code and diffs intact
  • Enabling persistent concise style without re-prompting
  • Educational demonstration of language compression and satire in AI tools

Strengths

  • Based on caveman's measured ~65% output token reduction
  • Persistent skill vs. ephemeral system prompts that drift over time
  • Explicit preserve list for code, errors, commands, and security warnings
  • Open source with MIT license and transparent benchmark plan

Considerations

  • Only reduces output tokens; input and reasoning tokens are unaffected
  • Skill activation costs ~1k input tokens per conversation
  • Thematic B vocabulary (e.g., doubleplusungood) can be net token negative
  • Expected savings are caveman-tier minus a small overhead from the theme

README quick start

Usage

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482