compressed-system-prompts

compressed-system-prompts is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 23 tokens per session (1,237 once invoked), scanned A, original, MIT.

A method for shortening system prompts, the instructions an AI receives before a conversation, by removing repetition and using compact commands and structure.

In plain words
What is it for?
Use it to rewrite long system prompts for coding agents or other AI systems.
Why use it?
It reduces repeated instruction text and makes the core rules easier for an AI agent to follow.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the major-ai-skills plugin — 147 skills, 8 plugins shipped together

Good fit Use it to rewrite long system prompts for coding agents or other AI systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/compressed-system-prompts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add alivirgo/Major-AI-Skills --skill compressed-system-prompts
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install major-ai-skills, the plugin that ships this one along with the rest of its 147 skills, 8 plugins.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for compressed-system-prompts

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/compressed-system-prompts/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/compressed-system-prompts)
Your own site
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/compressed-system-prompts"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/compressed-system-prompts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for compressed-system-prompts

Your own site · 80×15
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/compressed-system-prompts"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/compressed-system-prompts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,237 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.01237
Opus 5 $0.00012 $0.00619
Sonnet 5 $0.00005 $0.00247
Haiku 4.5 $0.00002 $0.00124

Measured yesterday against content hash 8875abe00098, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

compressed-system-prompts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/compressed-system-prompts/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compressed System Prompts (Prompt Minification Protocol)

Overview

Many production system prompts suffer from Rhetorical Bloat: long-winded, repetitive paragraphs written in conversational English ("You are a polite, helpful AI assistant. It is very important that you always strive to write clean, maintainable code, and please make sure to never introduce bugs or hallucinations...").

Rhetorical bloat dilutes attention weights, increases baseline turn latency, and wastes thousands of input tokens on every single turn.

The Compressed System Prompt Protocol minifies natural language instructions into high-density imperative grammar and structured XML tags, reducing system prompt token count by 70% while increasing model adherence and determinism.


Rhetorical Bloat vs. Minified Imperative Grammar

┌─────────────────────────────────────────────────────────────┐
│                 System Prompt Density Mapping               │
│                                                             │
│  Wordy Rhetorical System Prompt (480 Tokens):               │
│  "You are a coding assistant. Whenever a user asks you to   │
│   edit code, you should please make sure to read the file   │
│   carefully. It is critically important that you do not     │
│   make assumptions about functions that might not exist.    │
│   Always strive to write comprehensive unit tests with 100% │
│   coverage and please provide clean explanations..."        │
│  ↳ 480 tokens of polite fluff, diffuse attention            │
│                                                             │
│  Minified Imperative Token Structure (95 Tokens - 80% Cut): │
│  <role>Autonomous Senior Software Engineer</role>           │
│  <rules>                                                    │
│  1. Ingest line slices via `view_file` before editing.      │
│  2. Mutate files using `replace_file_content` (atomic).     │
│  3. Verify changes with unit tests (100% passing).          │
│  4. Zero conversational preamble. Pure code/diffs.          │
│  </rules>                                                   │
│  ↳ 95 tokens, 100% crisp deterministic instruction weights  │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 113 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · -13 tokens per session 8875abe00098
  2. 7d ago First seen · 113 lines · 36 tokens per session scan A 94724ebf77ee

Subscribe to this mod's changes

compressed-system-prompts is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,237 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories