AI Tooling
The training images ship with skills that teach coding agents this codebase's
configs, limits, and footguns. Claude Code
itself is not installed by default. Build with
--build-arg INSTALL_CLAUDE_CODE=1 to bake it in, or install it in a running
container with curl -fsSL https://claude.ai/install.sh | bash.
Using it
From a shell inside the container (bring your own subscription or API key):
Bash
cd /workspace && claudeDescribe the task. Four skills (parallelism, optimize, debug, docs) fire on
their own when relevant. The other six are user-invoked only: name them with
/launch, /checkpoints, /data, /add-model, /rl-setup, /write-tests.
What the agent reads
Every skill is grounded in agent-docs/ ↗, the same
reference this guide points to. The skills themselves live in
skills/ ↗ at the repo root as plain Markdown in the
Agent Skills format, readable by any tool. The
directory is tracked in the repo and copied into the images, so a local checkout
and the in-image agent both find it with no extra setup.
The rules the agent follows live in CLAUDE.md, with AGENTS.md symlinked to
it for other scaffolds.
Source on GitHubUpdated 18 November 2026