by sourcery-ai · AI Tool · ★ 1.9k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 1,875 |
| Forks | 100 |
| Category | AI Tool |
| License | MIT |
| Quality Score | 51/100 |
| Open Issues | 120 |
| Last Updated | 2026-10-07 |
| Created | 2019-07-15 |
| Est. Tokens | ~16k |
Sourcery - Instant AI Code Reviews Sourcery is here to help you: Speed up your code review process Improve your code quality and ensure high quality code Spend less time on reviews Accelerate development velocity What is Sourcery Sourcery is an automated code reviewer that will review any pull request on any GitHub repository to provide instant feedback on the proposed changes.
Looking for a sourcery alternative? If you're comparing sourcery with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code det
🚀 AI-powered code review tool for GitHub, GitLab, Bitbucket Cloud, Bitbucket Server, Azure DevOps and Gitea —
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman
An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as sec
Build effective agents using Model Context Protocol and simple workflow patterns
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI
Explore other popular ai tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: