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 5.5 | $0.00040 | $0.00631 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (14 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 1,577 once invoked, about $0.0004 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 2026-08-30.
ai-config-compress compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-config-compressfabis94/universal-ai-config | Skill | 14 | 2d ago | MIT | A | 100 | Claude Code, Codex |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 54 | Claude Code, Codex |
| prompt-engineerJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 93 | Claude Code |
| prompt-optimizationlangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 105 | 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 | today | Apache-2.0 | A | 228 | Claude Code |
| hve-buildermicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 54 | Claude Code |