_{Open GIF  ·  Run the example  ·  Still image}

bandr helps your coding agent turn the jobs captured in your logs into runnable Harbor task packages: the original instruction, starting environment, outcome verifier, and an oracle when one is available.

Bring logs and any existing harness or starting-state files. The coding agent writes source-specific parsers and generators; Mint runs them over the corpus, writes the packages, checks them, and records their provenance and gaps. Successful, failed, and partial runs can all contribute. Repeat attempts at the same instance become one task with their evidence kept together.

Traces → Harbor task → model attempt → verifier grade → new traces. Harbor can run an agent on the packaged task and grade its output using the task's verifier. The resulting trajectory and result can become input for another conversion. Use the tasks for evaluation or as environments in a training workflow.

Quickstart

Install bandr, then give your coding agent the bundled skill.

The package is bandr; its command is mint.

pip install bandr
mint skill install

_{Python 3.11+.}

Start a new Claude Code session and ask:

Use Mint to turn ./logs into Harbor tasks in ./mint-workspace.
Inspect the source first, build a few tasks, then validate and report.

The skill goes into ~/.claude/skills/mint/. Use mint skill install --project for the current project's .claude/skills/mint/. Other coding agents can read SKILL.md directly.

When to use Mint

Bring the starting-state files or harness when you have them. Missing evidence becomes a recorded gap or a candidate to finish, rather than an invented environment.

How it works

The coding agent writes source-specific code. Mint runs it over the corpus and records the evidence.

The output is a task package you can inspect:

out/tasks/<type>/<task>/
├── instruction.md          # the original job
├── environment/            # the world before the agent acted
├── tests/test.sh           # check the requested outcome
├── solution/solve.sh       # optional oracle
└── task.toml               # runtime configuration and provenance

The verifier checks the outcome; it does not require a new agent to replay the logged steps. Mint can also build dialogue tasks with a runtime user simulator, or use a model judge when deterministic grading is unsuitable.

Try it on three traces

The bundled example contains three synthetic attempts at two jobs. Two recorded answers are wrong. Its generator recomputes the expected answers from the starting files and builds two tasks.

Run it yourself: logs → parser → task generator → validation → report. No model calls or production logs are needed.

Local checks leave tasks generated. Install Harbor and start Docker, then run mint validate --runner harbor for container execution. Only passing Harbor execution gates can produce validated. The example's answer oracle proves verifier wiring; inspect that the expected answer follows from the inputs.

Documentation

Run mint --help, mint schema, and mint docs for the installed version's commands and contracts. Open an issue for a bug or a conversion case you cannot represent.

uv sync --extra dev
uv run ruff check bandits mint tests
uv run ruff format --check bandits mint tests
uv run pytest tests

_{Anonymous command usage is enabled by default. No log contents or paths are sent. Disable it with mint telemetry off or MINT_TELEMETRY_DISABLED=1. Captured fields and limits.}