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 multiplex-ai/muggle-ai-teams --skill geo-citabilitygit clone --depth 1 https://github.com/multiplex-ai/muggle-ai-teamsWrote 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/multiplex-ai/muggle-ai-teams/geo-citability)<a href="https://agentmods.dev/skills/multiplex-ai/muggle-ai-teams/geo-citability"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/geo-citability/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/multiplex-ai/muggle-ai-teams/geo-citability"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-teams/geo-citability.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.03542 |
| Opus 5.5 | $0.00024 | $0.01417 |
| Sonnet 5.5 | $0.00012 | $0.00708 |
| Haiku 4.5 | $0.00006 | $0.00354 |
Grade A, and why
geo-citability 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 5d 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.
This is a copy
100% identical to geo-citability — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Citability Scoring Skill
Core Insight
AI language models cite passages that meet specific structural criteria. Research from Princeton, Georgia Tech, and IIT Delhi (2024) found that GEO-optimized content achieves 30-115% higher visibility in AI-generated responses. The key finding: AI systems preferentially extract and cite passages that are 134-167 words long, self-contained (understandable without surrounding context), fact-rich (containing specific statistics, dates, or named entities), and directly answer a question in the first 1-2 sentences.
This is fundamentally different from traditional SEO copywriting, which optimizes for keyword density and user engagement metrics. GEO citability optimizes for extractability -- the ease with which an AI system can pull a passage from your content and present it as a direct answer.
Citability Scoring Rubric (0-100)
Category 1: Answer Block Quality (30% of total score)
This measures whether content contains clear, quotable answer passages that AI systems can extract verbatim.
Scoring Criteria:
| Score | Criteria |
|---|---|
| 90-100 | Every major section opens with a 1-2 sentence direct answer. Uses "X is..." or "X refers to..." patterns. First 40-60 words of each section can stand alone as a complete answer. |
| 70-89 | Most sections have clear answer openings. Some definition patterns present. Answers are identifiable but may need minor context. |
| 50-69 | Some sections have answer-like openings but many bury the answer in the middle or end of paragraphs. Few explicit definition patterns. |
| 30-49 | Answers are generally buried in long paragraphs. No consistent definition patterns. Content is narrative-driven rather than answer-driven. |
| 0-29 | No identifiable answer blocks. Content is entirely narrative, conversational, or fragmented. AI would struggle to extract any quotable passage. |
What to look for:
- Definition patterns: "X is [definition]." / "X refers to [explanation]." / "X means [meaning]."
- Answer-first structure: The answer appears in the first sentence, followed by supporting detail.
- Quantified answers: "The average cost of X is $Y" rather than "Many factors affect the cost of X."
- Comparison answers: "X differs from Y in three ways: [list]" rather than "X and Y are often confused."
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.
- 5d ago First seen · 320 lines · 61 tokens per session scan A e6b5edd38469
geo-citability is a skill published in the GitHub repository multiplex-ai/muggle-ai-teams (2 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 3,542 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to geo-citability, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
codex-handoff
Three-phase delivery workflow — Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff (via the codex-plugin-cc plugin). Implementation and review are never the same model. Use for any change touching more than one file or real…
discuss
Decision-lock workflow for complex features. Asks targeted domain-specific questions, locks scope, and writes a CONTEXT.md that downstream skills consume. Auto-invoked when a feature touches 3+ files across 2+ concerns, or manually via /discuss.
skill-name
One-line description of what this skill does and when it triggers.
codex-handoff
Three-phase delivery workflow — Claude plans and writes a spec, a Claude subagent implements in the host working tree, a fresh Codex session adversarially reviews the diff (via the codex-plugin-cc plugin). Implementation and review are never the same model. Use for any change touching more than one file or real…
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.