prompt-compressor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited prompt-compressor (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Compress verbose prompts/context before processing. Saves 40-60% tokens.
Invoke when:
/compress-prompt, /cptoken-formatter conventions| Remove | Transform To |
|---|---|
| "Please help me with" | (delete) |
| "I need you to" | (delete) |
| "Could you please" | (delete) |
| "I would like to" | (delete) |
| "I think", "Maybe", "Perhaps" | (delete) |
| "This might be a dumb question" | (delete) |
| "As I mentioned before" | (delete) |
| "For your reference" | (delete) |
| Verbose | Compressed |
|---|---|
| "I want to create a fn that takes X and returns Y" | fn(X) → Y |
| "The error message says..." | Error: ... |
| "In the file located at..." | File: ... |
| "I'm trying to..." | Goal: ... |
| "Here is my code..." | Code: |
| "The problem is that..." | Issue: ... |
See references/never_compress.md for full list:
## Compressed Prompt
[Compressed content]
---
Original: X tokens | Compressed: Y tokens | Saved: Z%Before (847 tokens):
Hello! I hope you're doing well today. I was wondering if you could please
help me with something. I'm trying to build a React application and I need
to create a custom hook that fetches user data from an API. The API is
located at /api/users and it returns a JSON response with the user object.
I would like the hook to handle loading states, error states, and also
cache the response. I think this might need to use useEffect and useState
but I'm not entirely sure about the best approach. Could you please help
me implement this? Here is some context about my project structure...
[500 more tokens of context]After (156 tokens):
Goal: Create React hook for user data fetching
Requirements:
- Endpoint: /api/users → JSON user obj
- Handle: loading, error states
- Cache response
Stack: React (useEffect, useState)
---
Saved: 82%Before:
I'm having a problem with my application. When I try to log in, I get an
error. The error message that appears on the screen says "TypeError: Cannot
read property 'map' of undefined" and it's happening in the UserList.tsx
file on line 42. I think the problem might be related to the API response
but I'm not sure. Here is my entire component file...
[entire 200-line file]After:
Error: TypeError: Cannot read property 'map' of undefined
File: UserList.tsx:42
Issue: API response may be undefined before .map()
Need: Null check or loading state| Level | Reduction | Use When |
|---|---|---|
| Light | 20-30% | Keep readability |
| Medium | 40-50% | Default |
| Heavy | 60-70% | Max compression |
Works w/ token-formatter skill:
# Compress prompt text
python scripts/compress_prompt.py "your prompt text here"
# Compress from file
python scripts/compress_prompt.py --file prompt.txt
# Set compression level
python scripts/compress_prompt.py --level heavy "text"fn=function str=string num=number bool=boolean
arr=array obj=object param=parameter
config=configuration env=environment
auth=authentication db=database
req=required opt=optional def=default→ = returns/produces & = and
| = or w/ = with
w/o = without ~ = approximately~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.