Update to Token Saver

{
  "description": "Shorten user-provided prose, notes, summaries, or prompts while preserving meaning and technical payloads. Use when asked to compress, condense, trim, or make supplied content more token-efficient.",
  "included_files": [],
  "name": "safe-text-compression",
  "skill_md_contents": "---\nname: safe-text-compression\ndescription: Shorten user-provided prose, notes, summaries, or prompts while preserving meaning and technical payloads. Use when asked to compress, condense, trim, or make supplied content more token-efficient.\n---\n\n# Safe text compression\n\n1. Identify the purpose, audience, and requested degree of compression. Ask only if ambiguity would materially change the result.\n2. Remove redundancy and low-value framing first; retain logical order and useful labels.\n3. Preserve negation, qualifiers, exceptions, names, dates, numbers, units, source attribution, uncertainty, requirements, and decision-relevant context.\n4. Leave code, commands, paths, URLs, identifiers, quoted errors, and existing code comments unchanged unless the user asks to edit them.\n5. Keep warnings, consent, safety constraints, and irreversible-action instructions. If space is limited, compress other material first.\n6. Compare the result against the source using the checklist in `references/compression-checklist.md`.\n7. Return the compressed version. Mention material omissions or tradeoffs explicitly; otherwise avoid an unnecessary change log.\n\nNever silently fabricate missing context or claim an exact token count. This skill does not run Caveman or a tokenizer. Preserve the original when a short version is not safe to rely on, especially for legal, medical, financial, security, or operational use.\n"
}