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 haoyu-haoyu/stata-ai-fusion --skill skillgit clone --depth 1 https://github.com/haoyu-haoyu/stata-ai-fusionWrote 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/haoyu-haoyu/stata-ai-fusion/skill)<a href="https://agentmods.dev/skills/haoyu-haoyu/stata-ai-fusion/skill"><img src="https://agentmods.dev/badge/skills/haoyu-haoyu/stata-ai-fusion/skill/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/haoyu-haoyu/stata-ai-fusion/skill"><img src="https://agentmods.dev/badge/skills/haoyu-haoyu/stata-ai-fusion/skill.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 | $0.00117 | $0.03849 |
| Opus 5 | $0.00059 | $0.01924 |
| Sonnet 5 | $0.00023 | $0.00770 |
| Haiku 4.5 | $0.00012 | $0.00385 |
Grade A, and why
stata-ai-fusion 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 12d 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 — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stata AI Fusion Skill
You have access to comprehensive Stata reference files. Do not load all files. Read only the 1-3 files relevant to the user's current task using the routing table below.
1. Execution Mode Detection
Detect which execution mode is available and adapt accordingly.
MCP Mode (Stata MCP Server Available)
When the MCP server is connected, you can execute Stata code directly:
- Use
stata_run_commandto run code and return results - Use
stata_run_do_fileto run full .do files - Use
stata_inspect_datato inspect loaded datasets (summary stats, variable info) - Use
stata_codebookto generate a codebook for the current dataset - Use
stata_get_resultsto retrieve stored estimation results (r(),e(),s()) - Use
stata_export_graphto export the current Stata graph to an image - Use
stata_search_logto search through Stata log output - Use
stata_install_packageto install community-contributed packages - Use
stata_cancel_commandto cancel a running Stata command - Use
stata_list_sessionsto list all active Stata sessions - Use
stata_close_sessionto close a specific Stata session - Always check execution results before proceeding
- If execution fails, read
references/error-codes.mdfor diagnosis
Offline Mode (No MCP Server)
When MCP is not available, generate code for the user to run manually:
- Write complete, self-contained .do files
- Include
version,clear all,set more offpreamble - Add
log usingfor output capture - Comment every non-obvious line
- Wrap risky operations with
captureand check_rc
Detection Logic
IF MCP tools are listed in available tools:
-> Use MCP execution mode
-> Run code incrementally, check results between steps
ELSE:
-> Use offline code generation mode
-> Produce complete .do file with full preamble
2. Core Coding Standards (Mandatory Rules)
Every piece of Stata code you generate MUST follow these rules. Violations cause silent bugs.
What ships with it
14 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.
- references/causal-inference.md 11 KB
- references/clinical-data.md 14 KB
- references/data-management.md 11 KB
- references/defensive-coding.md 8.1 KB
- references/econometrics.md 9.9 KB
- references/error-codes.md 8.5 KB
- references/graphics.md 12 KB
- references/mata.md 11 KB
- references/packages/coefplot.md 3.7 KB
- references/packages/gtools.md 2.4 KB
- references/packages/reghdfe.md 3.3 KB
- references/survival-analysis.md 8.4 KB
- references/syntax-core.md 13 KB
- references/tables-export.md 8.4 KB
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.
- 12d ago First seen · 495 lines · 117 tokens per session scan A c7f2f5fd82bf
stata-ai-fusion is a skill published in the GitHub repository haoyu-haoyu/stata-ai-fusion (43 stars, last pushed 2mo ago), licensed MIT. It adds 117 tokens to every session and 3,849 once invoked, about $0.0006 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
anomaly-characterization
SOP: Describe and classify anomalous phenomena that existing theory cannot explain.
anomaly-driven-abduction
Tactic: Inductive/abductive path — describe anomalous phenomena, generate candidate explanations, rank by plausibility.
fin-data-acquisition
A data-preparation workflow for financial research. It reads variable definitions from a completed research design and produces data-acquisition work plus executable Python or Stata regression scripts.
stata-regression
Run regression analyses in Stata with publication-ready output tables.
stata-skill
A packaged Stata Runner skill via official MCP-for-Stata server including statado, adopackageinstall, help, readlog and getdatainfo tools. Use it when (1) need to execute Stata do-file; (2) missing ado-packages; (3) find code error caused by syntax in Stata; (4) want to read smcl and text format log file with rich…
statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use…