Puts the right rules in context on every prompt, automatically — built for full-stack developers moving across frontend, backend, and SQL in one session, researchers working in bare or LaTeX-only directories, and teams who want adversarial review (security red/blue team, code critic) before merge.
222 rules across 30 domains, retrieved by relevance rather than dumped into CLAUDE.md, plus a plan-approval gate, session security hardening, and per-codebase lessons memory. Requires Python 3.10+ on
Skills 14 in the Claude listing
add Create a new Clawness rule from a natural language description. Audit rules Review one domain of the Clawness rule corpus for correctness against current official documentation, then record what was established as a version stamp (applies_to / verified / sources) on each rule bootstrap Author a starter set of Clawness rules for a project whose stack Clawness ships no corpus for (Ruby, PHP, Elixir, Haskell, C#, Swift, Dart, Scala, Clojure, ...). Claude md Shrink an oversized CLAUDE.md. Eval set Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed. messaging Write or rewrite the product's customer-facing copy — landing page, hero section, CTAs, onboarding, empty states, pricing, app-store and marketing pages — with the customer as the hero and the product Openclaw audit Trim an OpenClaw workspace's base system prompt. perf Run a performance audit on the project or a specific module. refresh Bring this project's Clawness rules up to date with the framework version it actually runs. review Run an adversarial code review on staged changes or a specific file. Security audit Run a stateful red team / blue team security audit on the current project or a specific module. status Show the current Clawness configuration: which rules are loaded, which agents are available, and how the hook is configured. test Generate comprehensive tests for a file or module. User docs Write user documentation for a project by scanning its codebase — its UI screens and its public API/CLI — inferring what someone can actually do with it, and drafting brief, task-oriented docs to the 