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 midspiral · Claude Skill · ★ 63
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is lemmafit safe to install? View the security audit →
lemmafit Make agents prove that their code is correct. Read our launch post: Introducing lemmafit: A Verifier in the AI Loop. Lemmafit integrates Dafny formal verification into your development workflow via Claude Code. Business logic, state machines, and other logic are written in Dafny, mathematically verified, then auto-compiled to TypeScript for use in your React app. Quick Start Use Cases / Considerations lemmafit works with greenfield projects. You typically begin a project with though provides rudimentary support for existing codebases. lemmafit compiles Dafny to Javascript/Typescript which then hooks into a runtime like a React app. In the future, we will support other languages. lemmafit is optimized to work with Claude Code. In the future, lemmafit will be agent-agnostic. How It Works Prompt Claude Code as you normally would. You may use a simple starting prompt or a structured prompting syst
| Stars | 63 |
| Forks | 4 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 70.9994017452816/100 |
| Last Updated | 2026-06-02 |
| Created | 2026-02-24 |
| Platforms | claude-code, node |
| Est. Tokens | ~8k |
Looking for a lemmafit alternative? If you're comparing lemmafit with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
📜 An MCP server for conversation history search and retrieval in Claude Code
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
Turns AI agents from chaotic code generators into disciplined engineers. 12-stage workflow from research to pr
Make Your Ideas Real. Build Apps, Websites and AI Agents with Plain English with Astro, React, Shadcn and Clou
This project provides a basic dev setup intended for Single Page Application (SPA) development. It contains ke
Explore other popular claude skill tools:
lemmafit is Make agents prove that their code is correct.. It is categorized as a Claude Skill with 63 GitHub stars.
lemmafit is primarily written in JavaScript. It covers topics such as ai, claude-code, dafny.
You can find installation instructions and usage details in the lemmafit GitHub repository at github.com/midspiral/lemmafit. The project has 63 stars and 4 forks, indicating an active community.
lemmafit is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to lemmafit on Agent Skills Hub include claude-historian-mcp, deepcontext-mcp, claudex. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: