distill

Agent command outputs are one of the biggest sources of token waste.

Logs, test results, stack traces… thousands of tokens sent to an LLM just to answer a simple question.

🔥 distill compresses command outputs into only what the LLM actually needs.

Save up to 99% of tokens without losing the signal.

How to use

Install:

npm i -g @samuelfaj/distill

Run onboarding:

distill

After onboarding you can use /distill skill in Claude / Codex or pipe command output into distill:

bun test 2>&1 | distill "Did tests pass? Return PASS or FAIL, followed by failing test names if any."
git diff | distill "What changed? Return only files changed and one-line summary for each."
terraform plan 2>&1 | distill "Is this safe? Return SAFE, REVIEW, or UNSAFE, followed by risky changes."

Recommended LLM: qwen3.5-4b

Example

rg -n "terminal|PERMISSION|permission|Permissions|Plan|full access|default" desktop --glob '!**/node_modules/**' | distill "find where terminal and permission UI are implemented in chat screen"

• Before: 7648 tokens 30592 characters 10218 words
• After: 99 tokens 396 characters 57 words
• 🔥 Saved ~98.7% tokens