clawness

add

Create a new Clawness rule from a natural language description. Describe what you want enforced and this will generate the YAML rule file with proper tags, triggers, and examples.

audit

Run a red team / blue team security audit on the current project or a specific module. Spawns adversarial sub-agents that probe for vulnerabilities and propose fixes. Use when reviewing security before deployment, after adding auth/payment code, or on a schedule.

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, ...). Researches the stack's current conventions from official documentation, drafts a small set of project rules into .clawness/rules/, lint-validates them, and stops for approval before writing anything. Run it when the SessionStart empty-coverage note fires, or whenever you want project rules for an uncovered stack.

claude-md

Shrink an oversized CLAUDE.md. Measures what the project's always-loaded instructions cost per turn, then works through it section by section — cutting what the codebase already says, moving path-specific guidance to .claude/rules/ and prompt-specific conventions to .clawness/rules/, and leaving load-bearing "don't undo this" content where it is. Destructive and deliberate: run it when you have the session to spend.

eval-set

Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed. Mirrors tests/ground_truth.json + `clawness eval`: you write prompt→expected-rule cases, then measure MRR@k and hit-rate before and after an edit. Run it after trimming a base prompt into ranked retrieval (see openclaw-audit / claude-md), or whenever you change rules and want proof retrieval still surfaces what matters.

openclaw-audit

Trim an OpenClaw workspace's base system prompt. Measures what the always-injected workspace files (SOUL.md, AGENTS.md, IDENTITY.md, USER.md, MEMORY.md) cost per turn, then works through them section by section — cutting what the tools or codebase already say, moving durable conventions to Clawness ranked retrieval (.clawness/rules/) and one-line traps to .clawness/memory.md, and leaving load-bearing persona and identity where they are. Destructive and deliberate: run it when you have the session to spend.

perf

Run a performance audit on the project or a specific module. Checks for N+1 queries, unnecessary re-renders, memory leaks, bundle size issues, and slow algorithms.

refresh

Bring this project's Clawness rules up to date with the framework version it actually runs. Establishes what is installed and what the codebase uses, looks up what changed since the rules were verified, and writes version-corrected overrides into .clawness/rules/ — reporting the list and stopping for approval before it writes anything. Run it when the SessionStart version-gap note fires, or whenever a major upgrade lands.

review

Run an adversarial code review on staged changes or a specific file. Spawns the code-critic agent to find bugs, performance issues, and missed edge cases. Use before merging PRs or committing.

status

Show the current Clawness configuration: which rules are loaded, which agents are available, and how the hook is configured. Use to understand what rules Claude is seeing for this project.