Playbooks

Start from what you are shipping

Each playbook names the third-party inputs the work pulls in, the exact use each one needs, and how the licenses you will meet fit that use, checked live against the license library. Run your real inputs through it, then hand your client a signed record they can verify.

• Ship a client website with third-party fonts, images, icons and code

  A launched website where every third-party font, image, icon set and front-end library has been checked for commercial web use, the required credits and notices are in place, and the client holds a signed rights manifest.

  startermedium risksupervised

  Inputs: Web fonts, Photos and illustrations, Icon sets, Front-end libraries · reviewed 2026-10-15

• Add an open-weight model to a commercial product feature

  A product feature served by an open-weight model, with the model license, any fine-tuning data and the serving stack checked for commercial deployment, the license conditions written into the product's terms, and a signed record of what was checked.

  intermediatehigh risksupervised

  Inputs: Base model weights, Your fine-tuned or adapted weights, Fine-tuning data, Inference server and libraries · reviewed 2026-10-15

• Distribute a desktop or mobile app that bundles open-source libraries

  A released app whose bundled libraries and assets have been checked for commercial redistribution, with copyleft obligations identified and met, a third-party notices screen, and a signed manifest per release.

  intermediatemedium risksupervised

  Inputs: Bundled libraries (unmodified), Libraries you modified, Bundled fonts and images · reviewed 2026-10-15

• Publish a client report or dashboard built on open data

  A published report or dashboard whose datasets, maps and charting libraries have been checked for commercial publication, with source attributions in place, share-alike obligations met, and a manifest the client can verify.

  startermedium risksupervised

  Inputs: Datasets, Map data, Charting and mapping libraries · reviewed 2026-10-15

• Deliver agent-made work with a rights record the client can verify

  Any deliverable — a design, an article, a codebase, a slide deck — handed over with a signed rights manifest listing every third-party input, the decision for each, and the duties that come with it, which the client verifies without an account.

  starterlow risksupervised

  Inputs: Third-party inputs · reviewed 2026-10-15

How a playbook works

1. Pick the playbook for what you are shipping. It lists the kinds of input the work pulls in and the intended use each needs, so you never have to work out which rights to ask for.
2. Check your inputs. Name each input's kind and license; the check answers allowed, blocked, needs review or insufficient evidence, with the conditions that come with it. Free, no account needed.
3. Resolve and hand over. Replace what is blocked, have a person review what needs it, then issue a signed rights manifest your client verifies without an account.

For agents

curl -s 'https://www.rightshold.com/v1/playbooks?q=client+website'
curl -s https://www.rightshold.com/v1/playbooks/check -H 'content-type: application/json' \
  -d '{"playbook":"ship-a-client-website","items":[{"kind":"fonts","license":"OFL-1.1","ref":"Inter"}]}'

MCP: find_playbooks and check_playbook at https://www.rightshold.com/mcp?toolset=playbooks.

Reviewed instructions. The rights checks the steps call run live against the license library; the rest of the workflow is guidance and has not been run for you. Playbook search orders by how well the text matches your query. Suppliers next to a playbook are live public listings in merit order (grade, then completed work); store listings by vetting tier, then verified ratings, then name. First-party listings are labelled. Nothing here is paid placement. Not legal advice.