agentmods.dev

stata-code: Instructions file for Claude Code

CLAUDE.md

stata-code CLAUDE.md is an instructions file for Claude Code from brycewang-stanford/stata-code. It costs 1,486 tokens per session, scanned A, original, MIT.

Project instructions for Stata Code, including communication preferences and how its Python package, VS Code extension, and GitHub release are published.

In plain words
What is it for?
Preparing and checking TestPyPI, PyPI, VS Code Marketplace, and GitHub releases, including running the local version check.
Why use it?
They help keep versions aligned across several files and publishing systems so the release checks do not fail.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is brycewang-stanford/stata-code's own configuration. It tells Claude Code how to work on stata-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stata-code configures →

not rated 55repo changed 1mo ago A scan 1,486 tokens original MIT
View source ↗ brycewang-stanford/stata-code
Reuse

Borrowing it

Nothing to install: this file belongs to brycewang-stanford/stata-code. 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/brycewang-stanford/stata-code/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/brycewang-stanford/stata-code

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.

agentmods badge for stata-code CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brycewang-stanford/stata-code/claude-md/github.svg)](https://agentmods.dev/instructions/brycewang-stanford/stata-code/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/brycewang-stanford/stata-code/claude-md"><img src="https://agentmods.dev/badge/instructions/brycewang-stanford/stata-code/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.

agentmods 80×15 button for stata-code CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/brycewang-stanford/stata-code/claude-md"><img src="https://agentmods.dev/badge/instructions/brycewang-stanford/stata-code/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,486 This file is loaded in full into every session.
When invoked 1,486 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01486 $0.01486
Opus 5.5 $0.00594 $0.00594
Sonnet 5.5 $0.00297 $0.00297
Haiku 4.5 $0.00149 $0.00149

Measured 1mo ago against content hash a23bf8abb1e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stata-code CLAUDE.md scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "%{http_code}\n" https://pypi.org/pypi/stata-code/X.Y.Z/json
CLAUDE.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — stata-code project notes

Project-specific guidance for Claude Code sessions in this repo. General publishing docs live in PUBLISHING.md; this file captures what isn't obvious from reading the workflows.

Communication

Please think and talk with me in English.

Release coordination

A unified release ships four artifacts under the same version number:

Channel Tag Workflow
TestPyPI (stata-code) vX.Y.Z publish-testpypi job in .github/workflows/release.yml
PyPI (stata-code) vX.Y.Z publish-pypi job in .github/workflows/release.yml
VS Code Marketplace (stata-code-vscode) vscode-vX.Y.Z .github/workflows/vscode-release.yml
GitHub Release vX.Y.Z tail end of release.yml

Eight version literals (across six files) must move together, or the release.yml "Verify tag matches project versions" gate (scripts/check_versions.py) fails the build before any publish runs. Bump all of them, or run the guard locally first (python3 scripts/check_versions.py --tag vX.Y.Z):

  1. pyproject.toml → [project] version
  2. stata_code/__init__.py → __version__
  3. stata_code/mcp/server.py → __version__
  4. vscode/package.json → version
  5. vscode/package-lock.json → top-level version and packages[""].version (two sites)
  6. .claude-plugin/plugin.json → version
  7. .claude-plugin/marketplace.json → metadata.version and each plugins[*].version (two sites)

vscode/src/mcpClient.ts imports the extension version from vscode/package.json for the MCP handshake, so it should not carry a separate literal.

PyPI / TestPyPI Trusted Publishing — what to know

Both PyPI and TestPyPI use OIDC (no API tokens in repo secrets). They are separate sites with separate publisher configs — each must be set up independently:

Site Manage URL Environment
PyPI https://pypi.org/manage/project/stata-code/settings/publishing/ pypi
TestPyPI https://test.pypi.org/manage/project/stata-code/settings/publishing/ testpypi

Read the full file on GitHub · 139 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.

  1. 1mo ago Changed · +11 lines · +119 tokens per session a23bf8abb1e2
  2. 2mo ago First seen · 128 lines · 1,367 tokens per session scan A ba8d695e1dab

Subscribe to this mod's changes

stata-code CLAUDE.md is an instructions file published in the GitHub repository brycewang-stanford/stata-code (55 stars, last pushed 10d ago), licensed MIT. It adds 1,486 tokens to every session, about $0.0059 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflowReleasesWriting and docsai-agentsanthropicclaudedata-analysisdata-scienceeconometrics
Related

stata-code CLAUDE.md compared with instructions from other repositories

stata-code CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
stata-code CLAUDE.mdbrycewang-stanford/stata-codeInstructions file5510d agoMITA1,486Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode