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 finna · Claude Skill · ★ 296
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Finn-loop safe to install? View the security audit →
Finn-loop Three Claude Code skills that turn Linear + GitHub into a small, human-gated AI software factory: idea → interviews you and files the issue → you label it → claims it and opens a PR → posts a verdict → you merge. Three skills, one approval label, one rule: humans merge. — researches the repo, interviews you until the behavior is unambiguous, then files a Linear issue with acceptance criteria () and non-goals (). — claims the next safe issue, implements only its contract, verifies it, and opens a PR. Runs repeatedly with . — reviews open PRs against their linked issue and required GitHub checks, then posts a three-group verdict. Runs repeatedly with . The prefix avoids collisions with Claude Code's bundled commands and with generic personal skills such as or . Requirements A Git repository hosted on GitHub, with a working remote Claude Code 2.1.71 or newer ( was added in that release) A Linear workspace and team The Linear connector enabled in Claude Code The GitHub CLI () authenticated with write access to the target repo At least one required GitHub status che
| Stars | 296 |
| Forks | 54 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 66.0808122910945/100 |
| Open Issues | 4 |
| Last Updated | 2026-07-23 |
| Created | 2026-07-22 |
| Platforms | claude-code, node |
| Est. Tokens | ~6k |
These tools work well together with Finn-loop for enhanced workflows:
Looking for a Finn-loop alternative? If you're comparing Finn-loop 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.
Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integratio
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integratio
The skill layer for AI agents: npm for AI Agent Skills.
Explore other popular claude skill tools:
Finn-loop is The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.. It is categorized as a Claude Skill with 296 GitHub stars.
Finn-loop is primarily written in JavaScript. It covers topics such as agentic-workflows, ai-agents, claude-code.
You can find installation instructions and usage details in the Finn-loop GitHub repository at github.com/finna/Finn-loop. The project has 296 stars and 54 forks, indicating an active community.
Finn-loop is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Finn-loop on Agent Skills Hub include ralph-starter, claude-codex-settings, SWE-AF. 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: