deva-cloak

A headed Chromium browser running in the Deva Cloak container, designed to appear like a normal user's browser during automated browsing.

In plain words
What is it for?
Use it for web scraping, browser automation, or checking how a site appears to a real browser.
Why use it?
It helps when ordinary automated browsers are blocked or scored as bots by services such as Cloudflare or reCAPTCHA.

Skill for Claude CodeCodex

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 skills/thevibeworks/deva/deva-cloak
Any agent
npx skills add thevibeworks/deva --skill deva-cloak
Clone the repo
git clone --depth 1 https://github.com/thevibeworks/deva

Made for: Claude Code, Codex.

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,785 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00123 $0.02785
Opus 5 $0.00062 $0.01392
Sonnet 5 $0.00025 $0.00557
Haiku 4.5 $0.00012 $0.00279

Measured 2d ago against content hash 9794d881c015, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deva-cloak 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 2d 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.

skills/deva-cloak/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deva-cloak: stealth browser in the deva cloak container

CloakBrowser is a custom-compiled Chromium with source-level fingerprint patches. Same Playwright API, different binary -- detection sites score it as a real browser because it is one. This image runs it headed by default on a virtual display, which passes checks that headless fails even with the patches.

Am I in the cloak context?

This skill only applies when the browser is actually present. ALWAYS run this check fresh -- never conclude from conversation context, a resumed session, or $DEVA_CLOAK alone (env markers can be scrubbed or stale; the binary is the ground truth):

command -v cloakbrowser >/dev/null && cloakbrowser info --quick

If that fails, you are in the base or rust image -- there is no CloakBrowser here. (DEVA_CLOAK=1 is baked into the cloak image as a convenience marker, but treat it as a hint, not the test.) Tell the user to relaunch with deva.sh -p cloak <agent>, or use the plain Playwright install (rust image) instead. Do not try to npm install cloakbrowser yourself; the binary is baked into the cloak image and a runtime install would download ~200MB and defeat the point.

What is baked in

  • Wrapper + playwright-core live in $CLOAK_APP_DIR (/opt/cloak).
  • Chromium binary is pre-downloaded, cache at /opt/cloakbrowser, auto-update off -- fully offline, no network needed to launch.
  • Free binary = Chromium 146 (58 fingerprint patches). No Pro license. Good enough for most sites and for viewing your own apps; the newest detection tricks (latest Cloudflare/DataDome) may still win. Pro (146->150, 71 patches) needs CLOAKBROWSER_LICENSE_KEY at runtime -- no rebuild.
  • Headed display: Xvfb on :99 + openbox, started by the entrypoint.
  • x11vnc for VNC into that display (interactive logins). Start it on demand (x11vnc -display :99 -rfbport 5900 -bg); on OrbStack/Linux the Mac reaches it directly at the container IP -- no port publish, no launch flag.
  • cloak-browserd always-on browser daemon (/usr/local/lib/cloak/cloak-browserd.mjs); OPT-IN, runs only with --cloak-browser, exposes CDP at CLOAK_CDP_ENDPOINT. Independent of VNC.

Read the full file on GitHub · 228 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. 2d ago First seen · 228 lines · 123 tokens per session scan A 9794d881c015

Subscribe to this mod's changes

deva-cloak is a skill published in the GitHub repository thevibeworks/deva (13 stars, last pushed 5d ago), licensed MIT. It adds 123 tokens to every session and 2,785 once invoked, about $0.0006 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 skills, from other repositories

harbor

CLI toolkit for managing containerized LLM services. Use when the user wants to start, stop, configure, or manage AI/LLM services like Ollama, Open WebUI, llama.cpp, vLLM, LiteLLM, ComfyUI, and 250+ others. Triggers on requests to "run a model", "start ollama", "set up an LLM", "configure harbor", "manage services"…

av/harbor · 114 tokens

project-writing-collectors

Best practices and orientation for AI assistants authoring or modifying Netdata data-collection plugins or modules in any language. Read before adding a new collector, modifying an existing one, working on logs, topology, NetFlow/sFlow/IPFIX, OTEL ingestion, SNMP profiles, statsd, Prometheus scraping, or interactive…

netdata/netdata · 147 tokens

temps

Manage, deploy, operate, and instrument applications with Temps. Use this skill whenever the user mentions Temps, @temps-sdk/[email protected], deploying or migrating an app to Temps, projects, environments, services, domains, backups, logs, monitoring, analytics, browser Performance Insights/Core Web Vitals, observability…

gotempsh/temps · 146 tokens

neo4j-nvl-skill

Neo4j Visualization Library (NVL) — framework-agnostic graph rendering for the browser. Covers @neo4j-nvl/base (NVL class, nodes/relationships, Canvas vs WebGL renderer), @neo4j-nvl/interaction-handlers (ZoomInteraction, PanInteraction, DragNodeInteraction, ClickInteraction, HoverInteraction, BoxSelectInteraction…

neo4j-contrib/neo4j-skills · 227 tokens

lov-app-generator

Use when the user asks for "App生成器", "生成 Web App", "生成 Tauri App", "生成原生 macOS App", "Finder Quick Action", "只创建 web", or to standardize an existing app with branding, CI/CD, native integration, and Lovinsp where applicable.

lovstudio/skills · 66 tokens

lov-integrate-lovinsp

幂等集成 lovinsp (click-to-code) 到当前前端项目,并支持从 code-inspector 自动迁移。 Use when the user asks to "装 lovinsp"、"集成 lovinsp"、"接入点击跳转源码"、"click to code"、 "从 code-inspector 迁移",or when scaffolding/upgrading a browser-rendered app that needs click-to-source support. Also trigger when another skill (例如 lov-app-generator) requires…

lovstudio/skills · 130 tokens