promptproof is an open-source command-line linter for AI agent prompt assets, including SKILL.md files, sub-agents, MCP tool descriptions, slash commands, and system prompts. It performs deterministic static checks for weak triggers, contradictions, token bloat, and invalid frontmatter without requiring an API.
promptproof sits in PulseGate's Code review & quality category. It focuses on catching weak, contradictory, bloated, or malformed AI agent prompt assets before they reach production. promptproof is an open-source project aimed at AI agent developers and prompt engineers. The project is open source (MIT). It runs on the command line, and it can be self-hosted.
Behind promptproof is shaxzodbek-uzb, and it first shipped in 2026. The project is developed in the open on GitHub with 6 commits in the last 90 days. Key capabilities include prompt linting, trigger analysis, and contradiction detection. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do