Pre-run prompt compression for iterative AI dev loops.
Scanned 9/7/2026
Install to Claude Code
npx -y skills add modbender/skill-library-mcp --skill compression --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Compression?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/modbender-compression)More formats (shields.io, HTML) on the badges page.
---
name: Trinity Compress (Skill)
description: Pre-run prompt compression for iterative AI dev loops.
---
# Trinity Compress (Skill)
Pre-run prompt compression for iterative AI dev loops.
**Goal:** reduce input tokens every iteration by compressing prompt files *before* your loop runs.
- Works with Ralph-style loops, agent/skill directories, and most token-billed providers.
- Runs as a **local script** (no model calls).
- Creates **.bak** backups and supports instant undo.
## What it installs into a repo
- `trinity-compress.config.json` — rules + targets
- `scripts/trinity-compress.sh` — compression script
- Makefile snippet (optional): `optimize-prompts`, `optimize-undo`, etc.
- `.gitignore` snippet: ignore `*.bak`
- Installers:
- `scripts/install.ps1` (Windows)
- `scripts/install.sh` (bash)
## Requirements
- bash 4+
- `jq`
- `bc`
## Use
1) Install into your repo (copy assets or use the included installer scripts)
2) Run:
- `bash scripts/trinity-compress.sh balanced`
- or via Makefile target
## Undo
- Restores all `*.bak` backups from the last run.
## Notes
- This tool does not rewrite code blocks, URLs, file paths, or variable names.
- Aggressive mode may reduce clarity; review before committing.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling