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 fabioc-aloha/Alex_Skill_Mall --skill semantic-model-disambiguationgit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/fabioc-aloha/alex_skill_mall/semantic-model-disambiguation)<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/semantic-model-disambiguation"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/semantic-model-disambiguation/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/fabioc-aloha/alex_skill_mall/semantic-model-disambiguation"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/semantic-model-disambiguation.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 | $0.00037 | $0.08252 |
| Opus 5 | $0.00018 | $0.04126 |
| Sonnet 5 | $0.00007 | $0.01650 |
| Haiku 4.5 | $0.00004 | $0.00825 |
Grade A, and why
semantic-model-disambiguation 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- semantic-overlap-detection — 88% identical, 219 lines differ
How it starts
The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Disambiguation
Read a reviewed disambiguation Excel workbook, extract approved rows, and apply changes to the live semantic model via MCP. This skill handles the execution phase — it assumes the semantic-overlap-detection skill has already produced the analysis and review Excel, and a domain expert has reviewed it.
Prerequisite: The semantic-overlap-detection skill must have been run first to produce output/disambiguation_analysis.json and output/disambiguation_results.xlsx in the plugin directory, and the domain expert must have set Review Status on all rows.
When to Use
- A domain expert has reviewed the disambiguation Excel and set Review Status to Approved/Rejected/Needs Discussion
- You need to apply approved column descriptions to the live model
- You need to hide excluded columns from the AI data schema
- You need to generate AI instructions text from approved business rules
Procedure
Step 1: Establish MCP Connection
MCP tool naming: This skill references tools by their VS Code MCP integration names (
mcp_powerbi-modeling-mcp_*). In other environments (Agency CLI, Claude Code), find the equivalent Power BI Modeling MCP server tools — the operations and parameters are the same, only the tool name prefix may differ.
The apply phase updates the live model via MCP tools. If the MCP connection has expired (e.g., the user reviewed the Excel in a different session), re-establish it:
-
Connect via
mcp_powerbi-modeling-mcp_connection_operations:- Fabric:
ConnectFabricwith workspace and dataset names - Desktop:
Connectwith port number
- Fabric:
-
Verify connection by listing tables via
mcp_powerbi-modeling-mcp_table_operations(operation:List).
Step 2: Read the Reviewed Excel
Use openpyxl (or the apply script's read_approved_items() function) to parse the Excel:
from scripts.apply_disambiguation_excel import read_approved_items
from pathlib import Path
# Plugin output directory
output_dir = Path(__file__).resolve().parent.parent.parent / "output"
descriptions, rules, exclusions = read_approved_items(output_dir / "disambiguation_results.xlsx")
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.
- 7d ago First seen · 629 lines · 37 tokens per session scan A 45f2bdfc984d
semantic-model-disambiguation is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 8,252 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 2026-09-03.
Other skills, from other repositories
ai-provider-anthropic-sdk
Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices.
ai-infrastructure-huggingface-inference
Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation, audio transcription, translation, summarization, and Inference Endpoints.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-infrastructure-replicate
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training.
ai-infrastructure-together-ai
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints.
ai-observability-langfuse
LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices.