Borrowing it
Nothing to install: this file belongs to brycewang-stanford/StatsPAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/brycewang-stanford/StatsPAI/main/AGENTS.mdgit clone --depth 1 https://github.com/brycewang-stanford/StatsPAIWrote 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/instructions/brycewang-stanford/statspai/agents-md)<a href="https://agentmods.dev/instructions/brycewang-stanford/statspai/agents-md"><img src="https://agentmods.dev/badge/instructions/brycewang-stanford/statspai/agents-md/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/instructions/brycewang-stanford/statspai/agents-md"><img src="https://agentmods.dev/badge/instructions/brycewang-stanford/statspai/agents-md.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 | $0.01341 | $0.01341 |
| Opus 5.5 | $0.00536 | $0.00536 |
| Sonnet 5.5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
StatsPAI AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — using StatsPAI from an AI agent
This file is for agents that use the package (coding assistants, MCP
clients, shell agents). Contributors to the repository read CLAUDE.md.
One import, one alias
import statspai as sp
Every public function is sp.<name> — no second-level imports. Examples,
docstrings and tests all use sp..
Discover → describe → call
sp.search_functions("staggered adoption event study") # ranked matches
sp.describe_function("callaway_santanna") # params, assumptions, failure modes, example
sp.function_schema("callaway_santanna") # JSON-Schema tool spec (agent_native=True adds x_statspai)
sp.route("did", design="staggered", timing_random="no") # data-free routing to the right call
sp.recommend(df, y="y", treatment="d", id="id", time="t") # routing from the data
sp.list_functions(kind="function") enumerates the callable functions
(sp.list_functions() also lists result and exception classes, which are not
tools). sp.search_functions understands Chinese queries too.
Example data
sp.list_datasets() # name, design, source, simulated, columns
df = sp.load_dataset("card_1995")
df.attrs["simulated"] # False: the real NLSYM extract
Several datasets are simulated replicas that carry the names of real ones
(mpdta, nsw_dw, basque_terrorism, german_reunification,
angrist_krueger_1991, currency_union_panel). An estimate on them describes
the simulation, not the published study: never report it as a finding about
the real data. Every frame carries attrs["simulated"], and the first load of
a replica in a process warns.
Read results the same way every time
r = sp.did(df, y="y", treat="d", id="id", time="t")
r.to_dict(detail="minimal") # the headline: estimate / se / pvalue / ci / alpha / n_obs
r.to_dict(detail="agent") # + diagnostics / violations / degradations / next_steps
r.violations() # failed assumption checks only; empty + degradations ≠ clean
r.next_steps() # follow-ups as dicts; `executable: True` runs as written with result / df bound
r.result_card() # estimand, sample, specification, inference, provenance (incl. seed), evidence tier
r.cite() # verified BibTeX; never write a citation from memory
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 Changed · +35 lines · +462 tokens per session 0681a74eb493
- 25d ago First seen · 75 lines · 879 tokens per session scan A 411cc4ef1a23
StatsPAI AGENTS.md is an instructions file published in the GitHub repository brycewang-stanford/StatsPAI (345 stars, last pushed yesterday), licensed MIT. It adds 1,341 tokens to every session, about $0.0054 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 2026-09-29.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).