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 joshft · Claude Skill · ★ 66
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is correctless safe to install? View the security audit →
Correctless Composable Claude Code skills that enforce a correctness-oriented development workflow. Spec before you code. Test before you implement. Never let an agent grade its own work. The Problem AI coding assistants are fast but sloppy. They write code that works for the happy path, skip edge cases, and silently introduce bugs that don't surface until production. The same model that wrote the code will review it and say "looks good" — because it's confirming its own decisions. Correctless fixes this by structuring the workflow so that every phase is executed by a different agent with a different lens: The spec agent asks "what does correct mean?" and researches current best practices before any code exists The review agent reads the spec cold and checks for security gaps, unstated assumptions, and untestable rules The tes
| Stars | 66 |
| Forks | 2 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.4173466539555/100 |
| Open Issues | 94 |
| Last Updated | 2026-09-04 |
| Created | 2026-03-27 |
| Platforms | claude-code, cli |
| Est. Tokens | ~15k |
Looking for a correctless alternative? If you're comparing correctless 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.
Primes your project for peak Claude Code performance
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency g
Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp
Transform Claude Code into a complete development platform with AI-powered commands that automate your entire
Tu equipo de desarrolladores en un plugin. 10 agentes, 11 skills planas, 18 comandos /alfred-dev:*. Memoria pe
Explore other popular claude skill tools:
correctless is The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.. It is categorized as a Claude Skill with 66 GitHub stars.
correctless is primarily written in Shell. It covers topics such as ai-development, ai-workflow, claude.
You can find installation instructions and usage details in the correctless GitHub repository at github.com/joshft/correctless. The project has 66 stars and 2 forks, indicating an active community.
correctless is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to correctless on Agent Skills Hub include optimus-claude, orchestkit, task-orchestrator. 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: