Onboard a repository

Talooner reviews every pull request against the policy in .talooner/rules.tln. Onboarding writes that first policy for you: it looks at how the repository is laid out, drafts rules that fit it, and writes a test suite next to them that proves each rule does what it says. You review the two files and commit them yourself.

It uses the same image as the pipeline step — nothing else to install.

What you need

Docker.
Your license key in TALOONER_LICENSE_KEY — from your license page (or get a free demo license).
Recommended: any LLM behind an OpenAI-compatible API — Qwen, DeepSeek, a model on your own servers… (TALOONER_MODEL_BASE_URL + TALOONER_MODEL + TALOONER_MODEL_API_KEY, examples); Anthropic and OpenAI also work with ANTHROPIC_API_KEY or OPENAI_API_KEY. With one, the rules are drafted for your repository and checked against their tests before you see them. Without one, you get the generic starter ruleset to edit by hand. Jev (JEV_URL + JEV_TOKEN) is supported too — it speeds up the reviews in your pipeline; drafting the rules still needs one of the LLMs above.

A repository on your machine

Run it from the repository's root folder:

cd path/to/your-repo
docker run --rm \
  -v "$PWD:/repo" --user "$(id -u):$(id -g)" \
  -e TALOONER_LICENSE_KEY \
  -e TALOONER_MODEL_BASE_URL -e TALOONER_MODEL -e TALOONER_MODEL_API_KEY \
  registry.gitlab.com/onlinecopyrig-rlr6226/talooner-runner:1 onboard

It writes two files into the repository:

.talooner/rules.tln        the rules
.talooner/rules.tln.test   a test for each rule

--user makes the files yours rather than the container's. If .talooner/rules.tln already exists and differs, onboarding stops — add --force to replace it.

A repository on GitHub or GitLab

Point it at a remote repository instead — no clone needed. It needs a token that can read the repository, and prints the two files instead of writing them (add --out <folder> to write them to a folder):

docker run --rm \
  -e TALOONER_LICENSE_KEY -e GITLAB_TOKEN \
  -e TALOONER_MODEL_BASE_URL -e TALOONER_MODEL -e TALOONER_MODEL_API_KEY \
  registry.gitlab.com/onlinecopyrig-rlr6226/talooner-runner:1 \
  onboard --repo gitlab.com/acme/shop

Use --repo github.com/acme/shop with GITHUB_TOKEN for GitHub. For self-managed GitLab or GitHub Enterprise, give the host — --repo git.acme.dev/team/shop — and --provider gitlab or github.

What it reads

Only the shape of the repository: the names of the top-level files and folders, the names of its CI workflows, and the first lines of the README. Never the source code. Those names go to the cluster running inside the container and, if you set an LLM key, to your own LLM provider. Nothing reaches us except the license check.

Then

Read .talooner/rules.tln and adjust it to how your team actually works — the draft is a starting point. The rules guide shows what rules can match on.

Run the tests after every change:

docker run --rm -v "$PWD:/repo" -w /repo --entrypoint tln \
  registry.gitlab.com/onlinecopyrig-rlr6226/talooner-runner:1 test .talooner/

Commit both files in a pull request.
Add the review step to your pipeline — onboarding prints the snippet for your CI, and the install guide has every option.

Let your coding agent do it

Onboarding comes as an agent skill too: a SKILL.md that tells your coding agent — Codex, Cursor, Claude Code, Qwen Code or any other — how to run onboarding in the current repository, tailor the drafted rules to the code it can see, keep the tests passing and open the pull request — always asking you before it commits.

Download SKILL.md

Put it where your agent picks up skills or instructions — its skills folder, or reference it from AGENTS.md — then ask your agent to "onboard this repo to Talooner".