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 fabis94/universal-ai-config --skill ai-config-compressgit clone --depth 1 https://github.com/fabis94/universal-ai-configWrote 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/fabis94/universal-ai-config/ai-config-compress)<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/ai-config-compress"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/ai-config-compress/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.
<a href="https://agentmods.dev/skills/fabis94/universal-ai-config/ai-config-compress"><img src="https://agentmods.dev/badge/skills/fabis94/universal-ai-config/ai-config-compress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 68 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00100 | $0.01577 |
| Opus 5 | $0.00050 | $0.00788 |
| Sonnet 5 | $0.00020 | $0.00315 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
ai-config-compress 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 11d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Compress
Compress LLM instructions with calibrated risk. Research shows ~60% of instruction tokens are removable without degrading output quality — and compression often improves performance by concentrating model attention.
Core Principles
- Instructions are the most sensitive prompt component. Apply maximum compression to examples and context, moderate compression to structure, minimal compression to core behavioral rules.
- Semantic equivalence ≠ behavioral equivalence. Two phrasings that mean the same thing to a human can produce different model behavior. Every change beyond mechanical cleanup carries nonzero risk.
- Compress in tiers. Apply safest changes first, present riskier changes as suggestions. The user decides how far to go.
Workflow
1. Analyze
Before compressing anything, analyze the input:
- Count tokens (estimate: words × 1.3 for English)
- Identify sections by function: safety, formatting, tone, behavior, examples, context, metadata
- Detect duplicates: rules that express the same constraint in different words
- Flag filler: politeness markers, hedging, verbose connectives
- Note structural issues: scattered related rules, inconsistent formatting
- Identify examples and assess whether they're redundant with stated rules
Present a brief analysis summary with estimated savings per tier.
2. Compress in Tiers
Apply changes tier by tier. For each tier, show a diff and token savings.
Tier 1 — Mechanical (auto-apply, safe)
These changes preserve exact meaning. Apply all of them:
- Fix typos and inconsistent punctuation
- Normalize whitespace (double spaces, trailing spaces, excessive blank lines)
- Apply word-level substitutions from
references/substitutions.md - Remove pure filler: "please note that," "it is important to," "keep in mind"
- Remove politeness in system prompts: "please," "kindly," "if you don't mind"
- Strip unnecessary articles in imperative instructions ("Write the response" → "Write response")
- Remove self-referential meta-commentary ("The following rules govern your behavior:" → just list the rules)
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.
- 11d ago First seen · 161 lines · 100 tokens per session scan A cbeeb47a4cfc
ai-config-compress is a skill published in the GitHub repository fabis94/universal-ai-config (11 stars, last pushed 15d ago), licensed MIT. It adds 100 tokens to every session and 1,577 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…