caveman-compress

Caveman Compress

Purpose

Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as <filename>.original.md.

Trigger

/caveman-compress <filepath> or when user asks to compress a memory file.

Process

1. Locate compress.js in the scripts/ directory adjacent to this SKILL.md.

2. Run the compression script as a single Bash command (agent does not read the file):

node /absolute/path/to/skills/caveman-compress/scripts/compress.js <absolute_filepath>

Where /absolute/path/to/skills/caveman-compress/ is the directory containing this SKILL.md. The <absolute_filepath> must be the full path to the file to compress.

3. The script handles everything in isolation:

   • Detects file type (no tokens — local check only)
   • Refuses sensitive filenames (.env, credentials, keys, etc.) before reading
   • Spawns a separate headless claude --print session to compress (the main agent never reads the file)
   • Validates output structure locally (no tokens)
   • If validation errors: spawns another headless session for targeted fixes only (no recompression)
   • Retries up to 2 times
   • If still failing after 2 retries: restores original, deletes backup, exits non-zero

4. Report the script's summary to the user. The summary looks like:

   Compressed CLAUDE.md: 706 → 285 bytes (-59.6%). Backup: CLAUDE.original.md
   

5. Do NOT read the file contents yourself. The script handles the entire operation and prints a summary.

Important: Isolation Architecture

The rewrite happens in an isolated headless session spawned by the script — not in the current session. This means:

• The main agent never ingests the file contents (no token cost)
• The headless child session runs with CAVEMAN_DEFAULT_MODE=off so it won't caveman-ify its own output
• There is no recursive trigger: the child receives a compress prompt on stdin, not a /caveman-compress slash command

Compression Rules

Remove

• Articles: a, an, the
• Filler: just, really, basically, actually, simply, essentially, generally
• Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend"
• Hedging: "it might be worth", "you could consider", "it would be good to"
• Redundant phrasing: "in order to" → "to", "make sure to" → "ensure", "the reason is because" → "because"
• Connective fluff: "however", "furthermore", "additionally", "in addition"

Preserve EXACTLY (never modify)

• Code blocks (fenced ``` and indented)
• Inline code (backtick content)
• URLs and links (full URLs, markdown links)
• File paths (/src/components/..., ./config.yaml)
• Commands (npm install, git commit, docker build)
• Technical terms (library names, API names, protocols, algorithms)
• Proper nouns (project names, people, companies)
• Dates, version numbers, numeric values
• Environment variables ($HOME, NODE_ENV)

Preserve Structure

• All markdown headings (keep exact heading text, compress body below)
• Bullet point hierarchy (keep nesting level)
• Numbered lists (keep numbering)
• Tables (compress cell text, keep structure)
• Frontmatter/YAML headers in markdown files

Compress

• Use short synonyms: "big" not "extensive", "fix" not "implement a solution for", "use" not "utilize"
• Fragments OK: "Run tests before commit" not "You should always run tests before committing"
• Drop "you should", "make sure to", "remember to" — just state the action
• Merge redundant bullets that say the same thing differently
• Keep one example where multiple examples show the same pattern

CRITICAL RULE: Anything inside ... must be copied EXACTLY. Do not:

• remove comments
• remove spacing
• reorder lines
• shorten commands
• simplify anything

Inline code (...) must be preserved EXACTLY. Do not modify anything inside backticks.

If file contains code blocks:

• Treat code blocks as read-only regions
• Only compress text outside them
• Do not merge sections around code

Pattern

Original:

You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.

Compressed:

Run tests before push to main. Catch bugs early, prevent broken prod deploys.

Original:

The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.

Compressed:

Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.

Boundaries

• ONLY compress natural language files (.md, .txt, .typ, .typst, .tex, extensionless)
• NEVER modify: .py, .js, .ts, .json, .yaml, .yml, .toml, .env, .lock, .css, .html, .xml, .sql, .sh
• If file has mixed content (prose + code), compress ONLY the prose sections
• If unsure whether something is code or prose, leave it unchanged
• Original file is backed up as FILE.original.md before overwriting
• Never compress FILE.original.md (skip it)
• Never compress files with sensitive names (.env, credentials.*, id_rsa, *.pem, etc.)