Skill Claude CodeCodex
Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or…
Skill Claude CodeCodex
Convert W&B Table artifacts into non-destructive EvalTable previews with scan-first planning, typed input/output/score columns, bounded batches, verification, and safe removal. Use when a coding agent needs to create, inspect, compare, verify, or remove W&B EvalTable previews.
Skill Claude CodeCodex
Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artifacts, Weave traces and evaluations, Reports, and Launch workflows. Use when the task spans multiple W&B surfaces or the user asks generally what is happening in a W&B project.
Plugin Claude Code
Track Claude Code sessions in Weave for observability and debugging.
Plugin Claude Code
Track Claude Code sessions in Weave for observability and debugging.
Instructions file CodexOpenCode
AGENTS.md instructions for wandb/weave-claude-code, covering agents.md, settled decisions: do not "fix" these, verifying traces, transcript lifecycle and config.
Instructions file
Claude Code instructions for wandb/weave-claude-code, a project described as: Claude Code plugin that traces sessions, tool calls, and subagents to W&B Weave for observability and debugging.
Hook
Runs when a session starts, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when a session ends, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when you submit a prompt, before the agent sees it, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when the agent finishes a response, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs on the StopFailure event, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs before the agent uses a tool, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs after a tool call finishes, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when a tool call fails, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when a subagent starts, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when a subagent finishes, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when the agent asks permission for an action, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs on the PermissionDenied event, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs when the agent sends a notification, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs before the context is compacted, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs after the context is compacted, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs after instructions files are loaded, executing hook-handler.sh via bash. From wandb/weave-claude-code.
Hook
Runs on the ConfigChange event, executing hook-handler.sh via bash. From wandb/weave-claude-code.