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.
npx skills add hackermanishackerman/claude-skills-vault --skill prompt-compressorgit clone --depth 1 https://github.com/hackermanishackerman/claude-skills-vaultWrote 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.
[](https://agentmods.dev/skills/hackermanishackerman/claude-skills-vault/prompt-compressor)<a href="https://agentmods.dev/skills/hackermanishackerman/claude-skills-vault/prompt-compressor"><img src="https://agentmods.dev/badge/skills/hackermanishackerman/claude-skills-vault/prompt-compressor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00046 | $0.01177 |
| Opus 5 | $0.00023 | $0.00589 |
| Sonnet 5 | $0.00009 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00118 |
Grade A, and why
prompt-compressor 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 8d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Compressor
Compress verbose prompts/context before processing. Saves 40-60% tokens.
When to Use
Invoke when:
- Input >1500 tokens
- User pastes entire files (needs only sections)
- Prompts have redundant phrasing
- Context includes irrelevant info
- Commands:
/compress-prompt,/cp
Process
- Identify core intent - What user actually wants
- Extract essential context - Only what's needed
- Remove redundant phrases - See rules below
- Apply abbreviations - Use
token-formatterconventions - Output compressed version - w/ token savings %
Compression Rules
Remove Phrases
| 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) |
Transform Patterns
| 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: ... |
Never Compress (Security)
See references/never_compress.md for full list:
- Auth headers, tokens, credentials
- Error stack traces (keep full)
- Security-related context
- API keys, secrets
- Exact error messages
- File paths in errors
Output Format
## Compressed Prompt
[Compressed content]
---
Original: X tokens | Compressed: Y tokens | Saved: Z%
Examples
Example 1: Verbose Request
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]
What ships with it
2 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.
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.
- 8d ago First seen · 172 lines · 46 tokens per session scan A 6a9fb843ea8f
prompt-compressor is a skill published in the GitHub repository hackermanishackerman/claude-skills-vault (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,177 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
prompting
Guide for writing effective system prompts for LLM agents. Use when creating or editing system prompts for applications, agent configurations, or development tools.
few-shot-examples
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
prompt-templates
Reusable prompt templates for construction AI tasks: cost estimation, schedule analysis, document processing, BIM queries. Structured prompts for consistent results.
opik-optimizer
Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.
prism
Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.