Why it is worth attention

It provides a structured, repeatable pattern for using AI agents in software development while maintaining strict human control over merges, and includes a detailed roadmap for evolving the system into a full factory with risk-aware merging, Slack integration, and persistent workers.

Who it is for

Software teams using Linear for issue tracking and GitHub for code hosting
Founders and CTOs exploring AI-assisted development workflows
Developers building automated code generation and review pipelines
Teams experimenting with agent-driven development under human oversight

Use cases

Transforming a rough idea into a well-defined Linear issue with acceptance criteria and non-goals
Having an AI agent automatically implement an issue from a spec and open a pull request
Automatically reviewing open PRs against their linked issue and CI checks to produce a verdict
Running a continuous loop of building and reviewing to process a queue of agent-ready issues

Strengths

Human-gated: only humans can apply the agent-ready label and merge, ensuring accountability
Clear contract-first approach: acceptance criteria and non-goals in Linear are the sole source of truth
Modular skills: finn-spec, finn-build, finn-review can be run independently or in loops
Well-documented growth path: the README provides concrete next steps for evolving from a starter loop to a full factory

Considerations

Requires Claude Code 2.1.71+, a Linear workspace with connector, and GitHub CLI authenticated—tight ecosystem lock-in
Session-dependent: /loop only runs while the Claude Code session is open, limiting unattended operation
Spec quality is the bottleneck; vague acceptance criteria lead to confident wrong PRs, and the system does not create CI for the target project

README quick start

Finn-loop

Three Claude Code skills that turn Linear + GitHub into a small, human-gated AI software factory:

idea → /finn-spec interviews you and files the issue → you label it agent-ready → /finn-build claims it and opens a PR → /finn-review posts a verdict → you merge.

Three skills, one approval label, one rule: humans merge.

skills/finn-spec — researches the repo, interviews you until the behavior is unambiguous, then files a Linear issue with acceptance criteria (AC-N) and non-goals (NG-N).
skills/finn-build — claims the next safe agent-ready issue, implements only its contract, verifies it, and opens a PR. Runs repeatedly with /loop /finn-build.
skills/finn-review — reviews open PRs against their linked issue and required GitHub checks, then posts a three-group verdict. Runs repeatedly with /loop /finn-review.

The finn- prefix avoids collisions with Claude Code's bundled commands and with generic personal skills such as /review or /build.

Requirements

A Git repository hosted on GitHub, with a working origin remote
Claude Code 2.1.71 or newer (/loop was added in that release)
A Linear workspace and team
The Linear connector enabled in Claude Code
The GitHub CLI (gh) authenticated with write access to the target repo
At least one required GitHub status check if you want fully automated loop-approved verdicts; without required CI, Finn-loop escalates the PR for human review

Recommended: connect Linear's GitHub integration so linked PRs can update issue status when they open and merge.

Install

Paste this into Claude Code inside the repo where you want the factory:

Set up Finn-loop from https://github.com/finna/Finn-loop.

1. Copy these files from that repo into this repo, preserving their contents:
   skills/finn-spec/SKILL.md   → .claude/skills/finn-spec/SKILL.md
   skills/finn-build/SKILL.md  → .claude/skills/finn-build/SKILL.md
   skills/finn-review/SKILL.md → .claude/skills/finn-review/SKILL.md

2. Ask for my Linear team key (for example ENG), then replace every TEAM
   placeholder in the copied skills with that exact key.

3. Check `claude --version` is 2.1.71 or newer.

Description

The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.

Related repositories

Similar projects matched by category, topics, and programming language.

S40911120

Featured

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI & Machine LearningLarge Language Models

bjan

Featured

claudemux

Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.

AI & Machine LearningAI Agents

hoainho

img2threejs

img2threejs reconstructs a 3D object from a single reference image as a procedural Three.js model using code-only, token-efficient, staged pipeline with quality gates, producing animation-ready Three.js groups.

Python

7,414