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/xidik12/oculo/claude-mdgit clone --depth 1 https://github.com/xidik12/oculoWrote 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/xidik12/oculo/claude-md)<a href="https://agentmods.dev/instructions/xidik12/oculo/claude-md"><img src="https://agentmods.dev/badge/instructions/xidik12/oculo/claude-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 | $0.02932 | $0.02932 |
| Opus 5 | $0.01466 | $0.01466 |
| Sonnet 5 | $0.00586 | $0.00586 |
| Haiku 4.5 | $0.00293 | $0.00293 |
Grade A, and why
oculo CLAUDE.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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oculo — AI-Powered Native Browser
Latin: "to see, to give sight" — Cursor:VSCode :: Oculo:Chrome
Quick Reference
- App ID:
com.oculo.browser - Version: 0.5.0
- Stack: Electron 34, TypeScript, React 19, Tailwind CSS 3, electron-vite
- Package manager: npm (not pnpm)
- Dev:
npm run dev(electron-vite hot reload) - Build:
npm run build→npm run dist:mac/npm run dist:win/npm run dist:linux - Typecheck:
npm run typecheck - Lint:
npm run lint - Clean:
npm run clean
Architecture
MCP Transport (HTTP, not stdio)
Electron's <webview> is only accessible from the renderer process, so we use HTTP:
Claude Code → bin/oculo-mcp.mjs (stdio bridge) → HTTP POST :19516/mcp
→ McpServerManager (main) → IPC 'mcp:tool-call' → Renderer → webview.executeJavaScript()
→ IPC 'mcp:tool-result' → HTTP response → stdio bridge → Claude Code
- Electron app starts HTTP server on ports 19516-19520, writes
~/.oculo-port(port:authtoken) bin/oculo-mcp.mjsis the stdio MCP bridge that Claude Code connects to — it reads~/.oculo-portand proxies
Register with Claude Code
claude mcp add oculo -- node ~/Desktop/oculo/bin/oculo-mcp.mjs
Tools are always discoverable (static definitions in bridge), but Oculo must be running for tool calls to succeed.
Minimal prompts (recommended)
claude mcp add oculo --allow-all -- node ~/Desktop/oculo/bin/oculo-mcp.mjs
This lets Claude use Oculo tools without per-call approval prompts. Combined with Autonomous Mode (Settings → Autonomous Mode), this gives zero-friction browser automation.
12 MCP Tools
| Tool | What it does | Token cost |
|---|---|---|
page |
Describe current page (headings, forms, buttons, links, text) | ~30-80 tokens |
act |
Navigate, click, hover, scroll, press keys, login (vault) | ~1 line |
fill |
Fill form fields by label matching, optional submit | ~1 line |
read |
Extract structured data (lists, tables, cards) | compact |
run |
Multi-step pipeline with conditionals (page/act/fill/read/wait/if) | header + last |
media |
Generate images (Nano Banana / DALL-E 3) or videos (Veo 3.1) | file path |
shell |
Execute shell commands non-interactively | stdout+stderr |
tabs |
List all open browser tabs | compact |
research |
Deep web research across multiple tabs | synthesized |
preview |
Pre-fetch URL without navigating | page description |
translate |
Translate page or text to any language | translated text |
lens |
Visual analysis via screenshot | description |
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 · 258 lines · 2,932 tokens per session scan A ac75dd791b9f
oculo CLAUDE.md is an instructions file published in the GitHub repository xidik12/oculo (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,932 tokens to every session, about $0.0147 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.
Other instructions, from other repositories
agentic-playwright common-tasks.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai prompt templates for agentic playwright, critical, instructions, phase 1: identify the task category and resolve paths and phase 2: select and customize the matching prompt template.
agentic-playwright debugging.instructions.md
Instructions for idavidov13/agentic-playwright, covering debugging, critical, capture defaults (this scaffold), built-in npm scripts for debugging and instructions.
agentic-playwright data-strategy.instructions.md
Instructions for idavidov13/agentic-playwright, covering data strategy, critical, file locations, instructions and phase 1: classify the value you need.
agentic-playwright config.instructions.md
Instructions for idavidov13/agentic-playwright, covering configuration, critical, file locations, instructions and phase 1: understand how env files are loaded.
agentic-playwright enums.instructions.md
Instructions for idavidov13/agentic-playwright, covering enums, critical, file locations, instructions and phase 1: decide if the value belongs in an enum.
agentic-playwright refactor-values.instructions.md
Instructions for idavidov13/agentic-playwright, covering refactoring enum values and static test data, critical, instructions, phase 1: find all consumers before touching anything and find all usages of the enum key.