Skip to main content

Getting started

1. Pick an agent

Any capable coding agent works: Claude Code, Codex, Cursor, Gemini CLI, … BAIT ships entry points for all of them (CLAUDE.md for Claude Code, AGENTS.md for the others).

2. Check data classification and provider handling

Most Biotic data are open, while some subsets are restricted or sensitive. Check IMR classification rules before sharing data or outputs. Local R/DuckDB execution does not guarantee that prompts, tools, logs, or outputs stay on-device. Review the active provider settings for transmission, retention, and training separately; a training opt-out is not a no-transmission guarantee. See Privacy.

3. Install BAIT — one prompt

In your agent, just say:

install https://github.com/DeepWaterIMR/BAIT

The agent takes it from there and walks you through:

  1. Privacy review — reviews classification and current provider handling settings.
  2. Clones BAIT to a sensible location — and refuses to install at a drive root like C:\ for security; it suggests a safe place in your home folder.
  3. Installs the skills globally, so BAIT works in every project without re-cloning.
  4. Sets up the database (asks first — it’s a big download). You’ll need IMR network access (VPN / HI-Adm Wi-Fi) and >2 GB of disk; the download runs in the background with a log and can take hours. Don’t run it over mobile internet or Starlink. The database lands at ~/IMR_biotic_BES_database/ (%USERPROFILE%\IMR_biotic_BES_database\ on Windows) — outside any repo, on purpose. Intranet is only needed for downloading/updating; querying is fully offline.
  5. Verifies the connection and shows you an example.

4. Ask your first question

“What is the largest cod in the database?”

Browse more in Example queries.

Keeping BAIT current

Say “update BAIT” — the agent runs git pull, re-syncs the global skills, and can refresh the database with updateDatabase() (changed years only in normal operation; intranet required). If the database schema changed, BioticExplorerServer safely performs a full rebuild.

If you use Fiskwise’s managed lifecycle, use its fiskwise-install and fiskwise-update skills instead of repeating the pack-level clone and skill-registration steps. Managed dependency checks honor saved R-install consent and project renv.lock; database refresh remains a separate opt-in choice. BAIT also remains usable on its own. Shared scientific writing, package-loading, and generic Quarto-reporting skills come from wise-writing and are installed on demand when needed.

How it learns

Useful solutions and corrections can first be recorded as project-local learning candidates with context, sanitized evidence, scope, confidence, and user corrections. After review, a sanitized reusable convention can be promoted to BAIT knowledge or the cookbook with its scope and uncertainty preserved. Candidates are never automatically published.