agentmods.dev

js-eyes AGENTS.md

js-eyes AGENTS.md is an instructions file for Codex, OpenCode from imjszhang/js-eyes. It costs 1,954 tokens per session, scanned A, original, MIT.

A set of repository rules for JS Eyes, a local browser-extension system that lets AI agents use browser capabilities under shared policies.

In plain words
What is it for?
It guides changes to browser operations, protocol code, policy handling, skill installation, client libraries, and host integrations.
Why use it?
It explains the boundaries between the extension, server, SDK, command-line tool, and policy packages, reducing the risk of putting behavior in the wrong layer.

Instructions file for CodexOpenCode

not rated 43 yesterday A scan 1,954 tokens original MIT
View the source file imjszhang/js-eyes
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/imjszhang/js-eyes/agents-md
Clone the repo
git clone --depth 1 https://github.com/imjszhang/js-eyes

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 js-eyes AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/imjszhang/js-eyes/agents-md.svg)](https://agentmods.dev/instructions/imjszhang/js-eyes/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/imjszhang/js-eyes/agents-md"><img src="https://agentmods.dev/badge/instructions/imjszhang/js-eyes/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,954 This file is loaded in full into every session.
When invoked 1,954 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 $0.01954 $0.01954
Opus 5 $0.00977 $0.00977
Sonnet 5 $0.00391 $0.00391
Haiku 4.5 $0.00195 $0.00195

Measured 5d ago against content hash 7c63823be36c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

js-eyes 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 5d 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 · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidance for Coding Agents

Project purpose

JS Eyes is a local-first browser capability and site-skill runtime for AI agents. The browser extension, server, SDK, CLI, MCP facade, and optional host adapters are separate layers over the same protocol and policy model.

CLI, MCP, and OpenClaw are peer host surfaces. Do not make a host-specific adapter the owner of behavior that belongs in the host-neutral runtime.

Repository map

  • apps/cli contains the public js-eyes command.
  • apps/native-host contains the browser Native Messaging host.
  • packages/protocol owns shared protocol constants, browser-operation metadata/handlers, and browser-operation catalogs. Install helpers live in @js-eyes/skill-install (not under protocol).
  • packages/skill-install owns skill discovery, install, trust, ZIP/npm, and registry helpers (formerly under protocol).
  • packages/policy owns PolicyContext and related egress/taint/task-origin policy primitives used by server-core and the client SDK.
  • packages/client-sdk owns the Node.js browser client (may re-export selected policy symbols from its main entry; prefer @js-eyes/policy directly).
  • packages/server-core owns the local HTTP and WebSocket server.
  • packages/mcp-server is the native stdio MCP facade.
  • packages/skill-contract validates Skill metadata; packages/skill-runtime owns host-neutral Skill Runtime V2, including isolated worker execution.
  • openclaw-plugin (@js-eyes/openclaw-plugin) is an optional OpenClaw adapter workspace. Core packages must not import it.
  • extensions/shared is the canonical source for cross-browser extension behavior. Chrome and Firefox copies are generated from it.
  • skills/* are independently versioned site skills.
  • packages/devtools owns builds, release staging, and generated artifacts.
  • distribution contains source templates for distributable artifacts.
  • src contains the public website source.
  • dist contains generated output and must not be edited by hand.

Read the full file on GitHub · 209 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. 5d ago First seen · 209 lines · 1,954 tokens per session scan A 7c63823be36c

Subscribe to this mod's changes

js-eyes AGENTS.md is an instructions file published in the GitHub repository imjszhang/js-eyes (43 stars, last pushed yesterday), licensed MIT. It adds 1,954 tokens to every session, about $0.0098 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

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

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

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 · 4,469 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