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/redf0x1/camofox-browser/copilot-instructionsgit clone --depth 1 https://github.com/redf0x1/camofox-browserWrote 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/redf0x1/camofox-browser/copilot-instructions)<a href="https://agentmods.dev/instructions/redf0x1/camofox-browser/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/redf0x1/camofox-browser/copilot-instructions.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 | $0.01198 | $0.01198 |
| Opus 5 | $0.00599 | $0.00599 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
camofox-browser copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CamoFox Browser — GitHub Copilot Instructions
What CamoFox Is
CamoFox Browser is an anti-detection browser automation server for AI agents. It wraps Camoufox (a Firefox fork with engine-level fingerprint spoofing) behind a TypeScript Express REST API and a camofox CLI. It is designed for agent workflows where deterministic element interaction, persistent user profiles, and structured output matter more than raw browser scripting.
Core Workflow (Snapshot-First)
- Create/open a tab (
openorPOST /tabs) - Capture snapshot (
snapshotorGET /tabs/:tabId/snapshot) - Choose refs from snapshot (
e1,e2, ...) - Interact (
click,type,fill,press,scroll, etc.) - Re-snapshot after major DOM changes/navigation
- Repeat until done, then close tab/session
Always prefer ref-driven interaction over brittle selectors.
Most-Used CLI Commands
# Lifecycle / navigation
camofox open <url> [--user <id>] [--viewport 1280x720] [--geo <preset>]
camofox navigate <url> [tabId] [--user <id>]
camofox go-back [tabId] [--user <id>]
camofox go-forward [tabId] [--user <id>]
camofox close [tabId] [--user <id>]
# Snapshot + inspection
camofox snapshot [tabId] [--user <id>]
camofox screenshot [tabId] [--output file] [--full-page]
camofox annotate [tabId] [--output file]
camofox get-url [tabId] [--user <id>]
camofox get-text [tabId] [--selector <css>] [--user <id>]
camofox get-links [tabId] [--user <id>]
camofox get-tabs [--user <id>]
# Interaction
camofox click <ref> [tabId] [--user <id>]
camofox type <ref> <text> [tabId] [--user <id>]
camofox fill '[e1]="user" [e2]="pass"' [tabId] [--user <id>]
camofox press <key> [tabId] [--user <id>]
camofox scroll [down|up|left|right] [tabId] [--amount 500]
camofox select <ref> <value> [tabId]
camofox hover <ref> [tabId]
camofox drag <fromRef> <toRef> [tabId]
# Utility
camofox wait <condition> [tabId] [--timeout 10000]
camofox eval "document.title" [tabId]
camofox search "query" [tabId] --engine google
camofox run <script-file> [--continue-on-error]
# Session / auth / server
camofox session save <name> [tabId]
camofox session load <name> [tabId]
camofox auth save <profile>
camofox auth load <profile> --inject --username-ref eX --password-ref eY
camofox server status
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.
- 5d ago First seen · 93 lines · 1,198 tokens per session scan A e4d56402b2df
camofox-browser copilot-instructions.md is an instructions file published in the GitHub repository redf0x1/camofox-browser (382 stars, last pushed 23d ago), licensed MIT. It adds 1,198 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
mcp-camoufox AGENTS.md
Instructions for RobithYusuf/mcp-camoufox, covering mcp-camoufox — agent guide, product and repository map, hard constraints, working defaults and architecture invariants.
stealth-cli AGENTS.md
Instructions for Youhai020616/stealth-cli, covering stealth-cli, project structure, key architecture decisions, camoufox-js api (do not guess) and error handling.
eyebrowse CLAUDE.md
Claude Code instructions for Evil-Bane/eyebrowse, covering claude.md — eyebrowse build notes, layout, run, pinned versions (lockstep matters) and key constraints (encoded in code — don't "simplify" away).
mcp-camoufox CLAUDE.md
Instructions for RobithYusuf/mcp-camoufox, a project described as: MCP server for stealth browser automation via Camoufox — 100+ tools, npx install, anti-bot stealth.
obscura AGENTS.md
AGENTS.md instructions for h4ckf0r0day/obscura, covering agents.md, build, rendering and stealth, no rendering, with rustls or stealth and test.
browser-harness CLAUDE.md
Claude Code instructions for browser-use/browser-harness, a project described as: Browser Harness | Self-healing harness that enables LLMs to complete any task.