oculos: Instructions file for Codex

AGENTS.md

oculos AGENTS.md is an instructions file for Codex, OpenCode from huseyinstif/oculos. It costs 3,121 tokens per session, scanned A, original, MIT.

A guide for controlling desktop applications through OculOS, a local interface that exposes their buttons, fields and other user-interface elements. It explains how to find windows and elements before interacting with them.

In plain words
What is it for?
Use it to list open windows, find buttons or input fields, inspect an application's interface tree, and trigger supported actions through OculOS.
Why use it?
It provides a repeatable way for an agent to discover the right application control instead of guessing. It also warns that element identifiers can change after a new search.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is huseyinstif/oculos's own configuration. It tells Codex and OpenCode how to work on oculos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oculos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to huseyinstif/oculos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/huseyinstif/oculos/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/huseyinstif/oculos

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 oculos AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/huseyinstif/oculos/agents-md/github.svg)](https://agentmods.dev/instructions/huseyinstif/oculos/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/huseyinstif/oculos/agents-md"><img src="https://agentmods.dev/badge/instructions/huseyinstif/oculos/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for oculos AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/huseyinstif/oculos/agents-md"><img src="https://agentmods.dev/badge/instructions/huseyinstif/oculos/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,121 This file is loaded in full into every session.
When invoked 3,121 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03121 $0.03121
Opus 5.5 $0.01248 $0.01248
Sonnet 5.5 $0.00624 $0.00624
Haiku 4.5 $0.00312 $0.00312

Measured 1mo ago against content hash 7e8e64323e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oculos 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 1mo 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 · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OculOS — AI Agent Instructions

You have access to OculOS, a local REST API that lets you read and control any desktop application through its UI Automation tree.

Base URL: http://127.0.0.1:7878

Auth: if the server was started with a token (or bound to a network address), send it on every request: X-OculOS-Token: <token> (or Authorization: Bearer <token>). GET /health returns auth_required and never needs the token. A 401 with code unauthorized means the token is missing or wrong — ask the user for it.


Core Workflow

1. list_windows          → find the target application (get pid / hwnd)
2. find_elements / tree  → locate the elements you need (get oculos_id)
3. interact              → act on those elements
4. wait / find again     → confirm the UI reached the state you expect

Element ids are stable. An oculos_id is 16 hex characters. Finding the same element again returns the same id, so you can re-run find as often as you like. An id stops working when the element disappears or after 30 minutes without use — you then get a not_found error: run find again and use the fresh id.


Discovery

List all windows

GET /windows

Returns: [{ pid, hwnd, title, exe_name, rect, visible }]

Search for elements (preferred — fast)

GET /windows/{pid}/find?q=Submit&type=Button&interactive=true
GET /hwnd/{hwnd}/find?q=Search&interactive=true

Parameters:

  • q — case-insensitive substring match on label or automation_id
  • type — element type filter, case-insensitive (see the list below; an unknown type → 400 invalid_input listing the valid ones)
  • interactive=true — return only elements that have at least one action

Element types: Window, Button, SplitButton, Edit, Text, CheckBox, RadioButton, ComboBox, ListBox, ListItem, TreeView, TreeItem, Menu, MenuBar, MenuItem, TabControl, TabItem, ToolBar, StatusBar, ScrollBar, Slider, Spinner, ProgressBar, Image, Link, Group, Pane, Dialog, Document, DataGrid, DataItem, Header, HeaderItem, Table, TitleBar, ToolTip, Separator, Calendar, Thumb, Custom, Unknown.

Read the full file on GitHub · 285 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. 1mo ago Changed · +71 lines · +1,443 tokens per session 7e8e64323e75
  2. 2mo ago First seen · 214 lines · 1,678 tokens per session scan A da1b91f3aec3

Subscribe to this mod's changes

oculos AGENTS.md is an instructions file published in the GitHub repository huseyinstif/oculos (134 stars, last pushed 1mo ago), licensed MIT. It adds 3,121 tokens to every session, about $0.0125 per session on Opus 5.5. 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

oculos AGENTS.md compared with instructions from other repositories

oculos AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
oculos AGENTS.mdhuseyinstif/oculosInstructions file1341mo agoMITA3,121Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot