compression
by trinitybotserver
AI & LLMsBrief
Pre-run prompt compression for iterative AI dev loops.
Description
What This Skill Does
A local script that compresses prompt files before AI dev loops run, reducing input token counts on each iteration. It preserves code blocks, URLs, file paths, and variable names. Creates .bak backups for instant undo.
Runs entirely locally with no model calls, so token savings happen at zero API cost.
When to Use It
- Cutting token costs before running long agent loops
- Batch-compressing skill directories before iterative dev sessions
- Reverting prompt changes when compressed output loses clarity
- Adding prompt optimization as a Makefile step in AI-heavy repos
- Trimming prompt files before submitting to token-billed API providers
Example Workflow
User asks: compress all prompts in my agent directory before running the dev loop
- 1
Installs trinity-compress.config.json with target paths and compression rules
- 2
Copies scripts/trinity-compress.sh into the repo
- 3
Runs bash scripts/trinity-compress.sh balanced
- 4
Reports token reduction and lists .bak backups created
Prompt files compressed with .bak backups saved; ready to run the agent loop with reduced token usage
Installation
clawhub install trinitybotserver/compressionRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.