compress-prompt

# Compress Prompt ## Goal Transform a prompt into the **minimal instruction** needed for the model to succeed. Not "preserve everything densely"—instead, "what's the least I need to say?" Output: Display compressed result + stats. Optionally write to file with `--output <path>`. ## Input `$ARGUMENTS` = prompt (file path or inline text) [--output path] If file path: read content. If inline: use directly. If ambiguous: try as file first. ## Principles 1. **Trust capability, enforce discipline** - Models know HOW to do tasks. But they cut corners, forget context, skip verification, declare victory early. Drop capability instructions, keep discipline guardrails. 2. **Goal over process** - State WHAT to achieve, not HOW. Let the model choose its approach. 3. **Training filter** - "Would a competent person need to be told this?" If no → drop it. Models are trained on millions of examples. 4. **Maximize action space** - Fewer constraints = more freedom = better results. Each constraint should earn its place. 5. **Inline-typable brevity** - Short enough you could type it verbally to a capable colleague. 6. **Avoid arbitrary values** - "Max 4 rounds" or "2-3 examples" become rigid rules. State the principle, not the number. Constrain productively while giving flexibility. ## What to Keep vs Drop | KEEP | DROP | |------|------| | Core goal/purpose | Process/phases (capability) | | Acceptance criteria (success conditions) | Examples the model knows | | Novel constraints (...