multi-repo-pr-creator 0.1.1

Simple workflow runner that applies change agents and opens PRs.

PR Creator

Simple workflow runner that clones target repos, applies changes via a change agent, and submits PRs.

Required tools

• Docker (for the cursor change agent)
• No git or GitHub CLI needed (Dulwich + GitHub API handle clone/push/PR)

Environment variables

Required

• CURSOR_API_KEY — passed to the cursor agent.
• GITHUB_TOKEN — used for push and GitHub PR creation.

Optional

• GIT_AUTHOR_NAME / GIT_AUTHOR_EMAIL — author/committer; defaults to pr-creator placeholders if unset.
• LOG_LEVEL — logging level; default INFO.
• CHANGE_AGENT — choose change agent; default cursor.
• EVALUATE_AGENT — choose evaluate agent; default cursor.
• NAMING_AGENT — choose naming agent; default cursor.
• CURSOR_IMAGE — docker image for cursor agent; default leonpatmore2/cursor-agent:latest.
• CURSOR_MODEL — cursor model to use; default gpt-5.2.
• CURSOR_ENV_KEYS — comma-separated env keys forwarded to the agent; default CURSOR_API_KEY.
• DATADOG_API_KEY / DATADOG_APP_KEY — required if using Datadog repo discovery.
• SUBMIT_CHANGE — submitter; default github.
• SUBMIT_PR_BASE — target base branch; default repo default.
• SUBMIT_PR_BODY — PR body; default Automated changes generated by pr-creator.
• DEFAULT_BRANCH_PREFIX — branch name prefix used when no change_id is provided; default auto/pr.
• GITHUB_DEFAULT_ORG — default GitHub org/owner to prepend when repo args are provided without an owner (e.g., --repo my-repo -> github.com/<org>/my-repo.git).

Commands

• pipenv run python -m pr_creator.cli --prompt "<prompt>" --relevance-prompt "<relevance>" --repo <repo_url> --working-dir .repos
• make test-e2e — run the e2e pytest (requires env vars set).
• make lint — flake8.
• make format — black (requires Python ≥3.12.6).

CLI arguments

Prompts

• --prompt — main prompt text. Required unless using prompt config.
• --relevance-prompt — relevance filter prompt. Required unless using prompt config.

Prompt config (alternative to passing prompts directly)

• --prompt-config-owner — GitHub owner of the prompt config repo. Must be set with --prompt-config-repo and --prompt-config-path.
• --prompt-config-repo — GitHub repo name containing the prompt config file.
• --prompt-config-ref — git ref for the prompt config file; default main.
• --prompt-config-path — path to the YAML prompt config file inside the repo.

Change ID (for static branches)

• --change-id — Change ID to use for static branch names. When provided, ensures re-runs use the same branch name (format: {branch_prefix}-{change_id}). Can also be set in prompt config YAML (takes precedence over CLI arg).

Repositories

• --repo — repository URL to process. Can be passed multiple times; required if not using Datadog discovery.

Datadog discovery

• --datadog-team — Datadog team name to discover repos (requires DATADOG_API_KEY and DATADOG_APP_KEY).
• --datadog-site — Datadog API base URL; default https://api.datadoghq.com.

Runtime

• --working-dir — where repos are cloned; default .repos.
• --log-level — logging level; default INFO.

Example (Docker)

docker run --rm \
  -e CURSOR_API_KEY \
  -e GITHUB_TOKEN \
  leonpatmore2/pr-creator:latest \
  --prompt-config-owner LeonPatmore \
  --prompt-config-repo pr-creator \
  --prompt-config-ref main \
  --prompt-config-path examples/prompt-config.yaml \
  --repo https://github.com/LeonPatmore/cheap-ai-agents-aws \
  --working-dir /tmp/repos \
  --log-level INFO