richmondsunlight.com AGENTS.md

AGENTS.md instructions for openva/richmondsunlight.com, covering agents.md, development environment, local development with docker, running tests and inside the web container.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/openva/richmondsunlight.com/agents-md
Clone the repo
git clone --depth 1 https://github.com/openva/richmondsunlight.com

Made for: Codex, OpenCode.

Per session 2,384 This file is loaded in full into every session.
When invoked 2,384 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02384 $0.02384
Opus 5 $0.01192 $0.01192
Sonnet 5 $0.00477 $0.00477
Haiku 4.5 $0.00238 $0.00238

Measured yesterday against content hash 9eddaf24f4f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

richmondsunlight.com 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 yesterday.

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.

AGENTS.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to LLMs when working with code in this repository.

Overview

Richmond Sunlight is a PHP-based website that tracks Virginia General Assembly legislation. The codebase has evolved over ~20 years and shows a mix of modern practices (Docker, CI/CD, SOA) alongside legacy patterns. The front-end (this repository) works with several companion systems: rs-api (API), rs-machine (scrapers/parsers), and rs-video-processor.

Development Environment

Local Development with Docker

Start the local environment:

./docker-run.sh

The site will be available at http://localhost:8000. The script will:

  • Download the rs-api repository if not present
  • Concatenate database dumps into a single file
  • Build and start Docker containers (web, api, db, memcached)
  • Wait for MariaDB to be available
  • Run site setup scripts

Stop the environment:

./docker-stop.sh

Running Tests

Run all tests (unit, integration, browser, security):

./docker-tests.sh

Run tests with full OWASP ZAP scan:

./docker-tests.sh --zap-full-scan

Skip browser tests:

./docker-tests.sh --no-browser-tests

Individual test scripts (run inside container):

# Inside the web container
/var/www/deploy/tests/run-all.sh       # All PHP tests
/var/www/deploy/tests/page-scan.php    # Page scanning
/var/www/deploy/tests/bill-test.php    # Bill unit tests
/var/www/deploy/tests/legislator-test.php  # Legislator tests
/var/www/deploy/tests/api.sh           # API tests

Dependency Management

Install PHP dependencies:

composer install

Install JavaScript dependencies:

cd htdocs/js/vendor
yarn install && yarn build

Code Quality

PHP linting (runs in CI):

find htdocs -name '*.php' -print0 | xargs -0 -n1 -P8 php -l

Pre-commit hooks are configured in .pre-commit-config.yaml for shell linting, PHP linting, and PHP-CS-Fixer.

Architecture

Directory Structure

  • htdocs/ - Public web root containing the front-end application
    • includes/ - PHP classes, functions, templates, and vendor dependencies
      • class.*.php - Class files (autoloaded)
      • functions.inc.php - Non-class utility functions
      • settings.inc.php - Configuration constants
      • templates/ - HTML templates
      • vendor/ - Composer dependencies
    • css/ - Stylesheets
    • js/ - JavaScript and client-side dependencies
    • images/ - Static assets (legislator photos, district maps)
    • Page files (bill.php, legislator.php, etc.)
  • api/ - Separate API application (rs-api repository, downloaded during docker-run.sh)
  • deploy/ - Deployment scripts, database schemas, tests
    • mysql/ - Database schema and seed data
    • browser-tests/ - Playwright browser tests
    • tests/ - PHP unit and integration tests
  • .github/workflows/ - CI/CD pipeline configuration

Read the full file on GitHub · 313 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. yesterday First seen · 313 lines · 2,384 tokens per session scan A 9eddaf24f4f2

Subscribe to this mod's changes

richmondsunlight.com AGENTS.md is an instructions file published in the GitHub repository openva/richmondsunlight.com (16 stars, last pushed 21d ago), licensed MIT. It adds 2,384 tokens to every session, about $0.0119 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 2026-09-01.

Related

Other instructions, from other repositories

congressMCP AGENTS.md

AGENTS.md instructions for amurshak/congressMCP, covering what this is, conventions and two sessions.

amurshak/congressMCP · 371 tokens

tw-formal-writing-standalone

台灣正式文件撰寫助手(獨立單檔版本,適用於 ChatGPT / Gemini)— 涵蓋政府公文、政府非公文文件、法律文件、人民對政府文書四類中文正式文件的撰寫(不含學術論文、商業文書、私人書信等,見下方排除清單)。 根據使用者意圖自動判斷文件類別,依照對應的撰寫規範與格式指引產出文件。 本檔案為完整獨立版本,所有規範與參考資料皆內含於此單一檔案中。 觸發此 skill 的情境: - 政府公文:簽、函、書函、公告、令、呈、咨、箋函、便簽、行文、發文、簽辦、擬稿、陳核、簽稿併陳、以稿代簽、先簽後稿、上行文、下行文、平行文 …

Imbad0202/tw-formal-writing · 30,006 tokens

tw-formal-writing CLAUDE.md

Instructions for Imbad0202/tw-formal-writing, covering claude.md, 這個 repo 是什麼, 內容架構:單一真實來源 → 多入口, 常用指令 and 改完 references/ 後重新生成 standalone.md 與 skills/(必跑,否則 ci fail).

Imbad0202/tw-formal-writing · 2,427 tokens

uk-legal-mcp CLAUDE.md

Instructions for paulieb89/uk-legal-mcp, covering claude.md — uk-legal-mcp, what this is, client ecosystems served, documentation index and commands.

paulieb89/uk-legal-mcp · 3,584 tokens

senado-br-mcp-cloudflare CLAUDE.md

Instructions for SidneyBissoli/senado-br-mcp-cloudflare, covering claude.md, project, commands, architecture and testing convention.

SidneyBissoli/senado-br-mcp-cloudflare · 4,150 tokens

spain-ai-kit AGENTS.md

Instructions for aplaceforallmystuff/spain-ai-kit, covering spain ai kit, what this is, spanish service mapping, api endpoints and ine (json-stat api).

aplaceforallmystuff/spain-ai-kit · 818 tokens