reticle — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by reticlehq · MCP Server · ★ 730

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is reticle safe to install? View the security audit →

About reticle

Your AI agent says "Feature complete." Then you open the app: ✗  a silent under a page that looks perfect   ✗  a flow that used to work, now broken   ✗  mock data where the real API should be Reticle is a proofreader for AI-written code. Your agent writes code. Reticle checks it against the real running app — the network calls, the store, the console, the things a screenshot can never show — and hands back pass, fail, or "couldn't tell", with the to fix. The agent fixes and retries until it passes, before you ever open the app. [](https://github.com/reticlehq/reticle/star

agent-skillagent-skillsagent-testingagent-verificationai-testing-toolautomated-testingclaude-codeclaude-skillsjevplaywright-mcp

Quick Facts

Stars730
Forks132
LanguageTypeScript
CategoryMCP Server
Quality Score63.8340273573395/100
Open Issues132
Last Updated2026-09-19
Created2026-06-11
Platformsbrowser, claude-code, mcp, node
Est. Tokens~21k

Compatible Skills

These tools work well together with reticle for enhanced workflows:

  • factif-ai — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • testdriverai — semantic(0.53)+complementary+rare_topics+similar_pop+shared_platform (63%)
  • qaskills — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (62%)
  • agent-skills-generator — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
  • openai-testing-agent-demo — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

reticle alternative? Top 6 similar tools

Looking for a reticle alternative? If you're comparing reticle with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agent-skills by oxylabs · ⭐ 875

    Official Agent skills of Oxylabs products

  • testdriverai by testdriverai · ⭐ 242

    Computer-Use SDK for E2E QA Testing

  • Claude-Code-Everything-You-Need-to-Know by wesammustafa · ⭐ 2.6k

    A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, sl

  • terraform-skill by antonbabenko · ⭐ 2.4k

    Terraform & OpenTofu Skill for AI Agents - testing, modules, CI/CD, and production patterns

  • autoprompt-skill by Spielewoy · ⭐ 1.2k

    Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

  • SkillForge by tripleyak · ⭐ 855

    A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baselin

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is reticle?

reticle is AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.. It is categorized as a MCP Server with 730 GitHub stars.

What programming language is reticle written in?

reticle is primarily written in TypeScript. It covers topics such as agent-skill, agent-skills, agent-testing.

How do I install or use reticle?

You can find installation instructions and usage details in the reticle GitHub repository at github.com/reticlehq/reticle. The project has 730 stars and 132 forks, indicating an active community.

What are the best alternatives to reticle?

The top alternatives to reticle on Agent Skills Hub include agent-skills, testdriverai, Claude-Code-Everything-You-Need-to-Know. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools