agentmods.dev

EOxElements AGENTS.md

Repository instructions for EOxElements, an npm workspaces monorepo containing several web-component packages and shared tools. They tell coding agents what to check before changing code and which project patterns to follow.

In plain words
What is it for?
Planning and implementing changes in the EOxElements repository, especially changes involving elements, attributes, properties, packages, or architectural boundaries.
Why use it?
They reduce guesswork before edits and help keep changes within the correct package or element. They also stop the agent when important details are unclear.

Instructions file for CodexOpenCode

34 5d ago A scan 3,209 tokens original MIT
View the source file EOX-A/EOxElements
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/eox-a/eoxelements/agents-md
Clone the repo
git clone --depth 1 https://github.com/EOX-A/EOxElements

Made for: Codex, OpenCode.

Per session 3,209 This file is loaded in full into every session.
When invoked 3,209 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 $0.03209 $0.03209
Opus 5 $0.01605 $0.01605
Sonnet 5 $0.00642 $0.00642
Haiku 4.5 $0.00321 $0.00321

Measured 2d ago against content hash 125e8ef68008, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

EOxElements 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 2d 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.

AGENTS.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md for EOxElements

Executable reference for AI agents working in this repo. Follow these rules literally.

1. Before Writing Any Code

Answer these questions in order. Stop if you can't answer one.

  1. Which element is changing? Identify the folder in /elements/ (e.g., elements/map).
  2. Is this a single-element change? If the request touches multiple elements, state that you will split it into atomic PRs/commits.
  3. New/changed attributes or properties?
    • Attributes: strings, numbers, booleans (HTML compatible).
    • Properties: Objects, Arrays, Functions (Complex types).
  4. What is the minimum change? State it in one sentence.
  5. Which existing pattern does this follow? (e.g., "following logic extraction pattern in src/methods/").

If any answer is "I don't know," stop. Ask a clarifying question. Do not guess.

2. Project Overview

EOxElements is an npm workspaces monorepo containing multiple published web component packages under the @eox/ scope, plus a shared utilities package (@eox/elements-utils) and an MCP server (@eox/elements-mcp-server).

  • Package name: @eox/elements (private, not published)
  • Module system: ESM ("type": "module")
  • Node requirement: >=24.0.0 (enforced via engine-strict=true in .npmrc)
  • Security Hardening: ignore-scripts=true is enabled in .npmrc. This means:
    • postinstall scripts (like Cypress binary download) are skipped. Run npx cypress install manually for local testing.
    • prepack scripts are skipped. When publishing or testing packaging, manually run npm run types:generate.
  • Package Quarantine: min-release-age=7 (days) is set in .npmrc to prevent the use of brand-new, potentially unverified package versions.
  • Component framework: Lit (v3.2+)
  • Language: JavaScript with JSDoc type annotations (NOT TypeScript source files)

3. Technology Stack

Category Technology
Component framework Lit 3.2+ (LitElement)
Language JavaScript + JSDoc (type-checked by TypeScript)
Bundler Vite (library mode per element)
Type checker TypeScript (checkJs mode, no .ts source)
Test runner Cypress (component + E2E)
Component mounting cypress-lit
Coverage Istanbul (vite-plugin-istanbul) + NYC
Storybook @storybook/web-components-vite (v10)
Linting ESLint (flat config) + @eox/eslint-config
Formatting Prettier
Release release-please (per-package automated releases)
CI/CD GitHub Actions
Design system @eox/ui (CSS variables + fonts)

Read the full file on GitHub · 235 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. 2d ago First seen · 235 lines · 3,209 tokens per session scan A 125e8ef68008

Subscribe to this mod's changes

EOxElements AGENTS.md is an instructions file published in the GitHub repository EOX-A/EOxElements (34 stars, last pushed 5d ago), licensed MIT. It adds 3,209 tokens to every session, about $0.0160 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.

FrontendPlanningWriting and docs
Related

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,345 tokens