What is nicar2026_skills_in_codex_claude CLAUDE.md?

Project guidance for a training repository that teaches how to create modular instruction packages called AI skills. Its examples cover election finance, weather, images, demographics, and skill creation.

Setting up Python with uv, launching JupyterLab, rendering Quarto documents, and developing or studying the included skills.

It explains the skill structure, setup tools, and learning materials so an unfamiliar contributor can navigate the project.

How amkessler/nicar2026_skills_in_codex_claude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to amkessler/nicar2026_skills_in_codex_claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/amkessler/nicar2026_skills_in_codex_claude/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/amkessler/nicar2026_skills_in_codex_claude

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/amkessler/nicar2026_skills_in_codex_claude/claude-md/github.svg)](https://agentmods.dev/instructions/amkessler/nicar2026_skills_in_codex_claude/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/amkessler/nicar2026_skills_in_codex_claude/claude-md"><img src="https://agentmods.dev/badge/instructions/amkessler/nicar2026_skills_in_codex_claude/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amkessler/nicar2026_skills_in_codex_claude/claude-md"><img src="https://agentmods.dev/badge/instructions/amkessler/nicar2026_skills_in_codex_claude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,959 This file is loaded in full into every session.

When invoked 1,959 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01959	$0.01959
Opus 5.5	$0.00784	$0.00784
Sonnet 5.5	$0.00392	$0.00392
Haiku 4.5	$0.00196	$0.00196

Measured 2mo ago against content hash 75a497c43a91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nicar2026_skills_in_codex_claude 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 2mo 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.

CLAUDE.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Demo project for NICAR 2026 showing how to use AI "skills" — modular, self-contained instruction packages that extend Claude/Codex's capabilities for domain-specific tasks. The repo includes six skills covering FEC campaign finance, weather forecasts, image rotation, county-level demographic analysis, and skill creation. The skills/ directory is the canonical session copy; numbered tutorial docs (01_*.md - 06_*.md) walk through quickstart workflows, skill-building exercises, and worked Census examples.

Environment Setup

This project uses uv for Python dependency management (Python 3.12+ required):

uv sync                          # Install dependencies into .venv
uv run <script>                  # Run a script with dependencies auto-resolved

JupyterLab is the primary analysis environment:

uv run jupyter lab               # Launch JupyterLab

Quarto renders notebooks/documents to data/html_reports/:

quarto render                    # Render all Quarto docs
quarto render <file.qmd>         # Render a single file

The .env file sets JUPYTER_PATH, JUPYTER_CONFIG_DIR, and JUPYTER_RUNTIME_DIR to keep Jupyter isolated inside .venv. This file is gitignored — do not commit it.

Skills Architecture

Skills are directories containing a SKILL.md (with YAML frontmatter) and optional bundled resources (scripts/, references/, assets/). This repo has three skill locations:

skills/ — session copy used in the NICAR conference session (canonical source)
.claude/skills/ — active skills for Claude Code (auto-loaded when you open the project)
.agents/skills/ — active repo-local skills for the Codex CLI

Six skills are present in all three locations:

fecfile — FEC campaign finance filing analysis (Python)
weather-forecast — 7-day forecasts via Open-Meteo (Python)
image-rotator — rotate images 90° (Python)
skill-creator — guided workflow for building new skills (Python)
state-county-rankings — ranked county metrics within a state (R, bundled CSV, no API key)
majority-minority-change — county racial composition change between two Census snapshots (R, bundled CSVs, no API key)

Read the full file on GitHub · 196 lines

Changes

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.

2mo ago First seen · 196 lines · 1,959 tokens per session scan A 75a497c43a91

Subscribe to this mod's changes

nicar2026_skills_in_codex_claude CLAUDE.md is an instructions file published in the GitHub repository amkessler/nicar2026_skills_in_codex_claude (21 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,959 tokens to every session, about $0.0078 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 2026-08-30.

nicar2026_skills_in_codex_claude CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nicar2026_skills_in_codex_claude CLAUDE.mdamkessler/nicar2026_skills_in_codex_claude	Instructions file	21	3mo ago	Apache-2.0	A	1,959	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

nicar2026_skills_in_codex_claude: Instructions file for Claude Code