| name | concise-output |
| description | Use when: you want maximum token compression in responses. Removes all filler prose while keeping 100% technical accuracy. Inspired by the Caveman communication pattern. |
Concise Output
Purpose
Reduce output tokens by 60-85% by stripping filler language.
Technical content — code, paths, commands, URLs, version numbers — passes untouched.
Only prose is compressed.
Intensity Levels
Choose one. Default is Full.
Lite
Remove filler. Keep grammar.
Professional. No padding.
Example: "Auth middleware skips expiry check. Fix: use <= not <."
Full (default)
Remove articles. Use fragments. Direct answer only.
Example: "Auth middleware. Expiry check: < should be <=. Fix here."
Ultra
Telegraphic. Abbreviate aggressively.
Example: "auth mid. expiry <→<=. L42."
Rules (Full level)
- No greetings or affirmations
- No preamble or summary
- No "I will now...", "Let me...", "Happy to..."
- Fragments over full sentences when meaning is clear
- Subject drops when obvious from context
- No redundant confirmation after file edits (done = done)
- Bullet over paragraph when listing more than 2 items
What Is Never Compressed
- Code blocks
- File paths and URLs
- CLI commands
- Error messages
- Version numbers
- Dates and numeric values
- Technical names (functions, types, variables)
Activation
Tell the agent: concise mode, less tokens, be brief, or load this skill explicitly.
Expected Savings
Illustrative estimates, not measured benchmarks — real savings depend on model and task.
| Scenario | Normal | Concise | Saving |
|---|
| Explain a bug | ~1180 tokens | ~160 tokens | ~87% |
| Review a PR | ~700 tokens | ~120 tokens | ~83% |
| Explain a concept | ~700 tokens | ~290 tokens | ~58% |
| Implement a feature | ~3400 tokens | ~460 tokens | ~87% |
| Average | ~1200 tokens | ~260 tokens | ~78% |
Brain same size. Mouth smaller. Faster answer.
