eidos — 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 agenticnotetaking · Agent Tool · ★ 59

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

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

About eidos

Eidos Spec-driven development plugin for Claude Code. Markdown specs capture intent. Code is a downstream manifestation of spec intent. The relationship is bidirectional: specs shape code, code can update specs, and conflicts become human decisions. Why Development intent lives in chat messages, commit messages, and the developer's head. When an AI starts a new session, it sees code but not the reasoning behind it. Eidos keeps intent in spec files alongside the code. Specs describe what a system should be. When spec and code drift apart, neither automatically wins — the human decides which to update. Three folders Specs describe timeless intent. Plans describe time-bound work. Code is the result. How it works Green-field Write a spec to capture what you want — behaviour, design, verification. This can be manual or collaborative ( walks you through it). Then push it into code: Verify — with tests, manually, or both. If something's off, update the spec, commit, push again. picks up the latest spec change and its precise diff. Repeat. Existing project You already have the manifestation — mine it for intent: Review the extracted spe

aiworkflowclaude-codemarkdownspecdrivendevelopmentspecification

Quick Facts

Stars59
Forks6
LanguagePython
CategoryAgent Tool
Quality Score63.577154638896/100
Last Updated2026-08-04
Created2026-02-17
Platformsclaude-code, python
Est. Tokens~15k

eidos alternative? Top 6 similar tools

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

  • C.R.I.S.P by radekamirko · ⭐ 52

    CRISP — The missing layer between vibe coding and building something people actually want.

  • Revornix by Qingyon-AI · ⭐ 290

    Revornix is an open-source, local-first AI information/markdown workspace. It helps you collect fragmented inp

  • claude-modular by oxygen-fragment · ⭐ 285

    Production-ready modular Claude Code framework with 30+ commands, token optimization, and MCP server integrati

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • mcp-server-typescript by dataforseo · ⭐ 242

    DataForSEO API modelcontextprotocol server

  • claude-gemini-mcp-slim by cmdaltctr · ⭐ 234

    Lightweight MCP integration bringing Google's Gemini AI capabilities to Claude Code with 1M+ token context win

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is eidos?

eidos is Spec Driven Development - claude code plugin - Sync between intent and implementation. It is categorized as a Agent Tool with 59 GitHub stars.

What programming language is eidos written in?

eidos is primarily written in Python. It covers topics such as aiworkflow, claude-code, markdown.

How do I install or use eidos?

You can find installation instructions and usage details in the eidos GitHub repository at github.com/agenticnotetaking/eidos. The project has 59 stars and 6 forks, indicating an active community.

What are the best alternatives to eidos?

The top alternatives to eidos on Agent Skills Hub include C.R.I.S.P, Revornix, claude-modular. 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 Agent Tool tools