Cloak Agent

C 69 completed
Cli Tool
unknown / typescript · tiny
42
Files
7,598
LOC
1
Frameworks
5
Languages

Pipeline State

completed
Run ID
#364698
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
57.50
Framework unique
Isolation
Last stage change
2026-05-10 03:35:10
Deduplication group #48503
Member of a group with 14 similar repo(s) — canonical #20404 view group →
Top concepts (2)
Project DescriptionTesting
Repobility · code-quality intelligence · https://repobility.com

AI Prompt

Create a command-line tool, similar to `cloak-agent`, designed for AI agents to interact with websites stealthily. The tool should be built using Go for the CLI and manage a background daemon process, possibly using Node.js/TypeScript for the daemon side that controls a stealth Chromium browser. I need functionality to navigate to a URL (`open`), take accessibility tree snapshots (`snapshot -i`), perform actions like clicking elements using references (`click @e1`), filling forms (`fill @e2 "email"`), and checking the stealth status (`stealth status`). The CLI should communicate with the daemon via a Unix socket.
cli go typescript node.js web-automation ai-agent command-line stealth playwright
Generated by gemma4:latest

Catalog Information

A command‑line tool that lets AI agents interact with websites stealthily, avoiding bot detection and minimizing token usage.

Description

Cloak‑Agent is a lightweight CLI that orchestrates a stealth Chromium browser patched to mimic a real user. It exposes a simple set of commands—open, click, fill, snapshot, and stealth status—that return concise, token‑efficient text. Snapshots are built from the page’s accessibility tree, providing element references instead of raw HTML, which cuts token consumption by 10‑50×. The tool is designed for AI agents, not humans, so each command is a single shell instruction with a deterministic response. It runs a Go binary that communicates with a background Node.js daemon managing the browser, ensuring low latency and persistent sessions. The result is reliable, undetectable web automation that fits naturally into AI pipelines.

الوصف

تُعد أداة Cloak‑Agent واجهة سطر أوامر خفيفة تُنظم متصفح كروم مخفي مُعدّل ليُظهر نفسه كمتصفح حقيقي. تُقدّم مجموعة بسيطة من الأوامر—فتح، نقر، ملء، لقطة، وحالة التمويه—التي تُرجع نصاً مختصراً وفعالاً من حيث استهلاك الرموز. تُنشئ اللقطات من شجرة الوصول للصفحة، ما يوفّر مراجع العناصر بدلًا من الـ HTML الخام، ويقلل استهلاك الرموز بمقدار 10‑50 مرة. تم تصميم الأداة لوكلاء الذكاء الاصطناعي، لذا كل أمر هو تعليمات شل واحدة مع استجابة محددة. تُشغّل البرنامج الثنائي بلغة Go الذي يتواصل مع خدمة خلفية Node.js تدير المتصفح، ما يضمن زمن استجابة منخفض وجلسات مستمرة. النتيجة هي أتمتة ويب موثوقة لا تُكشف، تتناسب بسلاسة مع خطوط أنابيب الذكاء الاصطناعي.

Novelty

8/10

Tags

browser-automation stealth-browsing ai-agent-integration token‑efficient-snapshots accessibility-tree-navigation detection-evasion

Technologies

ent

Claude Models

claude-opus-4.6

Quality Score

C
69.4/100
Structure
64
Code Quality
70
Documentation
62
Testing
70
Practices
74
Security
84
Dependencies
60

Strengths

  • Good test coverage (50% test-to-source ratio)
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • 385 duplicate lines detected \u2014 consider DRY refactoring
  • 2 'god files' with >500 LOC need decomposition

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency
  • Add a LICENSE file (MIT recommended for open source)

Security & Health

5.3h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (2)
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
Unknown
License
1.3%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

typescript
36.8%
json
24.0%
go
20.4%
markdown
18.4%
shell
0.5%

Frameworks

Vitest

Concepts (2)

Repobility · code-quality intelligence · https://repobility.com
CategoryNameDescriptionConfidence
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
auto_descriptionProject DescriptionBrowser automation CLI for AI agents that websites can't detect.80%
auto_categoryTestingtesting70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/88867.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV