Borrowing it
Nothing to install: this file belongs to Learning-Bayesian-Statistics/baygent-skills. 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/Learning-Bayesian-Statistics/baygent-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/Learning-Bayesian-Statistics/baygent-skillsWrote 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/learning-bayesian-statistics/baygent-skills/claude-md)<a href="https://agentmods.dev/instructions/learning-bayesian-statistics/baygent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/learning-bayesian-statistics/baygent-skills/claude-md.svg" alt="Measured on agentmods" 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 | $0.01343 | $0.01343 |
| Opus 5 | $0.00672 | $0.00672 |
| Sonnet 5 | $0.00269 | $0.00269 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
baygent-skills CLAUDE.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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project overview
baygent-skills is a collection of Agent Skills for Bayesian modeling, causal inference, and probabilistic thinking. Each skill is a self-contained subfolder following the Agent Skills spec.
Repo structure
baygent-skills/
├── bayesian-workflow/ # Shipped skill (v1.5, dual PyMC 5/6)
│ ├── SKILL.md # Main workflow instructions
│ ├── references/ # Detailed reference docs (priors, diagnostics, sensitivity, reporting)
│ └── scripts/ # diagnose_model.py, calibration_check.py, check_diagnostics.py
├── causal-inference/ # Shipped skill (v1.2)
│ ├── SKILL.md # Main workflow instructions (depends on bayesian-workflow)
│ ├── references/ # DAGs, quasi-experiments, structural models, refutation, reporting
│ └── scripts/ # check_refutation.py (calibrated causal language harness)
├── amortized-workflow/ # Shipped skill (v2.0, co-authored with Stefan Radev)
│ ├── SKILL.md # Amortized Bayesian workflow with BayesFlow
│ ├── references/ # Adapters, conditioning logic, model sizes, reporting
│ └── scripts/ # check_diagnostics.py, inspect_training.py
├── evals/ # Eval scenarios and benchmarks
│ ├── bayesian-workflow/ # 6 scenarios, 3 iterations
│ ├── causal-inference/ # 6 scenarios
│ ├── amortized-workflow/ # 6 scenarios + trigger set + benchmark results
│ └── smoke/ # Reporting-harness smoke test + cross-env (PyMC 5/6) equivalence gate
├── environment.yml # Mamba/conda env (env name: baygent, PyMC 5)
├── environment-pymc6.yml # Mamba/conda env (env name: baygent6, PyMC 6 / ArviZ 1.x)
├── LICENSE # MIT
└── CLAUDE.md # This file
Development conventions
Python environment
- Two envs during the PyMC 5 → 6 transition:
baygent(PyMC 5.28 / arviz 0.23 + arviz-stats/plots 1.0) —environment.yml. The causal-inference skill is pinned here (CausalPy capspymc<6).baygent6(PyMC 6.0.1 / arviz 1.x + pymc-extras 0.12) —environment-pymc6.yml. The bayesian-workflow scripts run on both; that dual run is the compatibility guarantee.
- Run
conda run -n baygent python <script>(or-n baygent6). Recreate withmamba env create -f environment.yml/mamba env create -f environment-pymc6.yml - Never use system Python
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.
- 8d ago First seen · 67 lines · 1,343 tokens per session scan A d56d77dcc9dc
baygent-skills CLAUDE.md is an instructions file published in the GitHub repository Learning-Bayesian-Statistics/baygent-skills (172 stars, last pushed 3d ago), licensed MIT. It adds 1,343 tokens to every session, about $0.0067 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.