What is promptCompressor?

A rule-based tool that shortens prompts while preserving their meaning, technical terms, code, JSON templates, and web addresses. Prompt compression means removing unnecessary words before a prompt is sent to an AI system.

Use it to compress prompts, measure how much text was removed, improve compression rules, and check that shortened prompts still retain their meaning.

It can reduce the amount of text processed, which may lower token use and API costs. Its fixed rules make the changes predictable and easier to inspect.

promptCompressor — Skill for Claude Code by AlirezaSoltaniJazi

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 AlirezaSoltaniJazi/Skillnir --skill promptcompressor

Clone the repo

git clone --depth 1 https://github.com/AlirezaSoltaniJazi/Skillnir

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/promptcompressor/github.svg)](https://agentmods.dev/skills/alirezasoltanijazi/skillnir/promptcompressor)

Your own site

<a href="https://agentmods.dev/skills/alirezasoltanijazi/skillnir/promptcompressor"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/promptcompressor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alirezasoltanijazi/skillnir/promptcompressor"><img src="https://agentmods.dev/badge/skills/alirezasoltanijazi/skillnir/promptcompressor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,951 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.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.01951
Opus 5.5	$0.00029	$0.00780
Sonnet 5.5	$0.00015	$0.00390
Haiku 4.5	$0.00007	$0.00195

Measured 1mo ago against content hash d3c070f5d6b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

promptCompressor 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate-compressor.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.data/skills/promptCompressor/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before You Start

Read LEARNED.md first. It contains corrections and conventions from previous sessions.

Announce skill usage. Always say "Using: promptCompressor skill" at the very start of your response.

When to Use

Working on src/skillnir/compressor.py — the core compression module
Debugging or improving compression rules (word sets, phrase replacements)
Analyzing compression ratios on pipeline prompts
Adding new protected zone patterns
Working on the compression toggle in settings
Reviewing whether compressed prompts preserve meaning

Do NOT Use

General Python backend — use backendEngineer
UI/settings page layout — use frontendEngineer
CI/CD and pre-commit — use devopsEngineer

Architecture

src/skillnir/compressor.py          # Core module — compress_prompt()
src/skillnir/backends.py            # Integration — build_subprocess_command() + maybe_compress_prompt()
src/skillnir/ui/pages/settings.py   # Toggle — compress_prompts config
tests/test_compressor.py            # 51 unit tests

Data flow: Pipeline prompt string -> build_subprocess_command() (subprocess backends) or maybe_compress_prompt() (Claude SDK backend) -> compress_prompt() -> compressed string -> CLI subprocess / SDK call

Integration points: Two call sites in backends.py, both gated on compress_prompts=True in AppConfig: build_subprocess_command() compresses inline for subprocess backends; maybe_compress_prompt() is the shared wrapper for the async-SDK path and is called from generator.py, docs_compressor.py, docs_optimizer.py, rule_generator.py, wiki_generator.py, and skill_generator.py.

Compression Algorithm

Applied in order:

Detect protected zones — code blocks, inline code, JSON templates, URLs, file paths, markdown headers, YAML frontmatter, table rows, indented code blocks
Replace verbose phrases — "in order to" -> "to", "due to the fact that" -> "because" (~30 pairs)
Remove stop words — articles, auxiliaries, intensifiers, fillers (outside protected zones)
Collapse whitespace — normalize spaces and blank lines

Read the full file on GitHub · 160 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · +16 lines d3c070f5d6b6
2mo ago First seen · 144 lines · 73 tokens per session scan A 1afa669e9164

Subscribe to this mod's changes

promptCompressor is a skill published in the GitHub repository AlirezaSoltaniJazi/Skillnir (9 stars, last pushed 12d ago), licensed MIT. It adds 73 tokens to every session and 1,951 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Data and AI Prompting

promptCompressor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
promptCompressorAlirezaSoltaniJazi/Skillnir	Skill	9	12d ago	MIT	A	73	Claude Code
llm-app-patternsdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	54	Claude Code, Codex
prompt-engineerJeffallan/claude-skills	Skill	12k	7d ago	MIT	A	93	Claude Code
prompt-optimizationlangwatch/langwatch	Skill	5.0k	yesterday	Apache-2.0	A	105	Claude Code, Codex
omh-model-optimizationrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	84	Claude Code, Codex
ideogram4digitalsamba/claude-code-video-toolkit	Skill	2.5k	yesterday	MIT	A	99	Claude Code
prompt-library-for-startupsaws/agent-toolkit-for-aws	Skill	3.4k	yesterday	Apache-2.0	A	228	Claude Code