agent-js AGENTS.md

agent-js AGENTS.md is an instructions file for Codex, OpenCode from elanmed/agent-js. It costs 764 tokens per session, scanned A, original, MIT.

Project-specific instructions for developing and testing the agent-js Node.js project. They define the required tools, coding conventions, testing expectations, and commands to run after changes.

In plain words
What is it for?
Use them when modifying agent-js to follow its Node.js and pnpm workflow, run linting, type checks, tests, and formatting, and write assertions and code in the project’s required style.
Why use it?
They give an automated coding agent consistent rules for making changes in that repository. This reduces avoidable style violations, missing tests, and incomplete checks.

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/elanmed/agent-js/agents-md
Clone the repo
git clone --depth 1 https://github.com/elanmed/agent-js

Made for: Codex, OpenCode.

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 agent-js AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/elanmed/agent-js/agents-md.svg)](https://agentmods.dev/instructions/elanmed/agent-js/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/elanmed/agent-js/agents-md"><img src="https://agentmods.dev/badge/instructions/elanmed/agent-js/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 764 This file is loaded in full into every session.
When invoked 764 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 $0.00764 $0.00764
Opus 5 $0.00382 $0.00382
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 3d ago against content hash d439e06c0124, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-js 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 3d 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-js

You are running in a container. Make all changes to /agent-js at the root of the filesystem.

This is a Node.js project. Only Node.js APIs should be used. Use node for running and testing, and pnpm as the package manager.

Development

After every change, run linting, types, tests, and formatting:

pnpm run lint
pnpm run types
pnpm run test
pnpm run format

Or all at once:

pnpm run ci

Guidelines

  • Never add comments
  • Minimize diffs — only change what's necessary
  • All changes must have test coverage
  • Prefer assert.deepStrictEqual over multiple individual field assertions — check the whole object in one call
  • Never use content: result.content in deepStrictEqual assertions — it's a tautology. Inline the actual expected value
  • Never use assert.ok(result.includes(...)) — assert on the whole string with assert.equal or assert.strictEqual
  • Only use === and !==; never use ==, !=, or truthy/falsy coercions like if (obj) or if (!obj). Use ! only on boolean expressions
  • For string assertions with newlines: use template literals when the string contains any newline that is not a single trailing one. If it's just a single trailing newline, use "...\n" instead
  • For fs, import fsDeps directly from deps.ts. In tests, use setupFakeDeps() from test-helpers.ts to mock all fs methods, processEnv, and processStdout globally. Use testFs._files / testFs._dirs / testFs._globResults to set up fixture state. Import testFs and setupFakeDeps from ./test-helpers.ts.
  • processEnv.get and processStdout.write are also in deps.ts and mocked by setupFakeDeps(). Use testProcessEnv._set(key, value) for env vars. Override processStdout.write with an additional mock.method(processStdout, "write", ...) if you need to capture output.
  • Pure utility functions do not need deps — import and call them directly in tests.

fs mocking example

Production code:

import { fsDeps } from "./deps.ts";

export function readConfig() {
  if (fsDeps.existsSync("config.json") === false) return null;
  return JSON.parse(fsDeps.readFileSync("config.json").toString());
}

Read the full file on GitHub · 86 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. 3d ago First seen · 86 lines · 764 tokens per session scan A d439e06c0124

Subscribe to this mod's changes

agent-js AGENTS.md is an instructions file published in the GitHub repository elanmed/agent-js (2 stars, last pushed 3d ago), licensed MIT. It adds 764 tokens to every session, about $0.0038 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 2026-08-31.

Related

Other instructions, from other repositories

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

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

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

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

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

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