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.
npx agentmods add instructions/cdcgov/cdc-open-viz/agents-mdgit clone --depth 1 https://github.com/CDCgov/cdc-open-vizWrote 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/cdcgov/cdc-open-viz/agents-md)<a href="https://agentmods.dev/instructions/cdcgov/cdc-open-viz/agents-md"><img src="https://agentmods.dev/badge/instructions/cdcgov/cdc-open-viz/agents-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 | $0.02268 | $0.02268 |
| Opus 5 | $0.01134 | $0.01134 |
| Sonnet 5 | $0.00454 | $0.00454 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
cdc-open-viz 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 4d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions
This file helps AI coding assistants understand how to work with this repository. Use it as an index to these sections:
- Testing Commands: Required testing strategy plus targeted/quick/full test commands.
- Test Discovery & Storybook MCP: How AI tools locate tests, story files, and the shared test helpers.
- Branch Comparison: Default base branch for feature diffs.
- Context Documents: Deep guidance for specific systems and workflows.
- Config Documentation Maintenance: Rules for keeping package
CONFIG.mdfiles and shared config docs up to date.
Branch Comparison
Feature branches usually branch from dev; compare against dev by default when determining what a feature contains.
Testing Commands
Use repo-local script commands for consistency (yarn ...) and avoid relying on a globally installed lerna.
Required Test Strategy
- Default to targeted tests for the files/components you changed.
- If changes span many areas, run quick suites.
- Do not run full suites unless the user explicitly asks for them.
Targeted Tests (Default)
For unit targeting, copy this root command shape exactly; both -- separators are required.
- Unit tests for one package/file:
- Use package-relative test file paths after
--scope, not repository-root paths. yarn test-unit:quick -- --scope @cdc/<package-name> -- src/.../<file>.test.<js|jsx|ts|tsx>- Example:
yarn test-unit:quick -- --scope @cdc/dashboard -- src/test/CdcDashboardComponent.test.tsx
- Use package-relative test file paths after
- Storybook tests for one story file:
yarn test-storybook:quick packages/.../_stories/<file>.stories.<js|jsx|ts|tsx>- Example:
yarn test-storybook:quick packages/chart/src/_stories/ChartEditor.stories.tsx
Quick Suites (For Broad Changes)
- Unit quick mode (bypasses standalone build checks by setting
COVE_QUICK_TESTS=1):yarn test-unit:quick
- Storybook quick mode (sets
COVE_QUICK_TESTS=1and excludes files matching*.smoke.stories.<js|jsx|ts|tsx>):yarn test-storybook:quick
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.
- 4d ago First seen · 140 lines · 2,268 tokens per session scan A 5cfff4954826
cdc-open-viz AGENTS.md is an instructions file published in the GitHub repository CDCgov/cdc-open-viz (55 stars, last pushed today), licensed Apache-2.0. It adds 2,268 tokens to every session, about $0.0113 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
semiotic AGENTS.md
AGENTS.md instructions for nteract/semiotic, covering semiotic repository instructions, scope, source map, repository layout and working agreements.
ag-charts AGENTS.md
AGENTS.md instructions for ag-grid/ag-charts, covering ai agent instructions, ambiguity and confidence, project overview, critical rules and pre-commit requirements.
ag-charts CLAUDE.md
Claude Code instructions for ag-grid/ag-charts, a project described as: AG Charts is a fully-featured and highly customizable JavaScript charting library. The professional choice for developers building enterprise applications.
pygwalker CLAUDE.md
Instructions for Kanaries/pygwalker, covering claude.md and tl;dr for a coding agent.
semiotic CLAUDE.md
Claude Code instructions for nteract/semiotic, covering semiotic claude code instructions and claude code notes.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.