flashtype — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 opral · Codex Skill · ★ 291

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

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

About flashtype

Flashtype The markdown editor for Claude & Codex Agents edit. You review the diff. Nothing lands without you. Download for macOS - Website - Lix - Discord Write Markdown With Agents In The Loop Flashtype is a WYSIWYG markdown editor with Claude Code and Codex built in. Point it at a folder, open the files you already have, and run coding agents against the same files from a real terminal beside your document. When an agent edits, Flashtype shows the change as an inline diff with word-level precision. Accept or reject each change before it lands, browse document history, and restore earlier versions when you need to. Features Built on the Lix SDK, an embedd

claude-codecodexmarkdown

Quick Facts

Stars291
Forks29
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score62.7897961177894/100
Open Issues20
Last Updated2026-09-26
Created2025-03-06
Platformsclaude-code, codex, node
Est. Tokens~14k

Compatible Skills

These tools work well together with flashtype for enhanced workflows:

  • codex-collab — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)
  • Noteriv — semantic(0.39)+complementary+same_lang+similar_pop+shared_platform (59%)
  • claude-skills — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • mcp-read-website-fast — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)

flashtype alternative? Top 6 similar tools

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

  • claude-codex-settings by fcakyon · ⭐ 1.2k

    Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM

  • codexia by milisp · ⭐ 927

    Lightweight Agent Workstation for Codex + Claude code — with dots, task scheduler, git worktree & remote contr

  • memorix by AVIDS2 · ⭐ 825

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • claude-conversation-extractor by ZeroSumQuant · ⭐ 675

    Extract clean conversation logs from Claude Code's internal storage

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • codex-mcp-server by tuannvm · ⭐ 636

    MCP server wrapper for OpenAI Codex CLI that enables Claude Code to leverage Codex's AI capabilities directly.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is flashtype?

flashtype is The markdown editor for Claude & Codex. It is categorized as a Codex Skill with 291 GitHub stars.

What programming language is flashtype written in?

flashtype is primarily written in TypeScript. It covers topics such as claude-code, codex, markdown.

How do I install or use flashtype?

You can find installation instructions and usage details in the flashtype GitHub repository at github.com/opral/flashtype. The project has 291 stars and 29 forks, indicating an active community.

What license does flashtype use?

flashtype is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to flashtype?

The top alternatives to flashtype on Agent Skills Hub include claude-codex-settings, codexia, memorix. 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 Codex Skill tools