Use when cutting a new bully release — bumping the plugin version so Claude Code users get an update notification. Triggers include "cut a release", "ship a new version", "release vX.Y.Z", "bump the version", or "publish an update to bully".
Authors, modifies, or removes rules in `.bully.yml`. Use when the user says "add a lint rule for X", "ban Y", "tighten <rule-id>", "make <rule-id> a warning", "convert <rule-id> to semantic", "remove <rule-id>", "change the scope of <rule-id>", or asks to apply recommendations from `/bully-review`. Always tests a rule against a fixture before writing it to the config.
Bootstraps a project's .bully.yml by detecting the tech stack from manifest files, migrating rules from existing linting tools, and generating a baseline config. Use when user says "init agentic lint", "set up agentic lint", "bootstrap lint config", "create lint rules", "bully init", "initialize agentic lint", or asks to create or generate an agentic lint configuration.
Interprets bully PostToolUse hook output after Edit/Write -- fixes blocked-stderr violations or dispatches the bully-evaluator subagent for semantic payloads.
Reviews bully rule health from the telemetry log. Use when the user says "review my lint rules", "check rule health", "which lint rules are noisy", "find dead lint rules", "bully review", or asks for an audit of `.bully.yml`. Surfaces noisy, dead, and slow rules and suggests which to adjust, remove, or promote.