woz-benchmark
**woz-benchmark** Runs a side-by-side performance comparison of WOZCODE versus vanilla Claude Code on a user's own git repository by executing the same coding prompts twice with fresh repo resets between runs. Use this to measure real cost, token count, turn count, and wall-clock time savings when choosing between WOZCODE and standard Claude Code for development workflows.
git clone --depth 1 https://github.com/WithWoz/wozcode-plugin /tmp/woz-benchmark && cp -r /tmp/woz-benchmark/skills/woz-benchmark ~/.claude/skills/woz-benchmarkSKILL.md
`/woz-benchmark` was renamed. Invoke the **woz** skill and run its `benchmark` subcommand (equivalent to `/woz benchmark`).
WOZCODE free-plan fallback agent — active when the monthly free-plan cap is exhausted. Claude Code's built-in Read, Edit, Write, Grep, Glob, and NotebookEdit are available; WOZCODE MCP tools are disallowed until the cap resets or the user upgrades.
WozCode enhanced coding agent with smart search, batch editing, and SQL introspection. Use as the default main thread agent.
Fast read-only agent for file searches, symbol lookups, and codebase questions like "where is X defined?", "where is X called?", or "how does X flow through the system?". Prefer over shell-based exploration when answering would take 3+ Search/Sql calls. Cheaper model (haiku) so delegation pays for itself on any real scan.
Deprecated alias — use `/woz login`.
Deprecated alias — use `/woz logout`.
Search past Claude Code sessions to recall commands, solutions, and context from prior conversations. TRIGGER on 'remember when', 'last time', 'we did this before', 'how did we', or /woz-recall.
Show the WOZCODE savings report — calls saved, time saved, tokens saved, and lifetime totals.
Deprecated alias — use `/woz status`.