bork

Create a conventional commit message by analyzing staged changes

Drive a goal to a merged endpoint — orchestrate the offload architect loop with contextual plan reviews, a push-based wait bridge, and gate-judged merge

Chains /review + /design-review + /qa into a single workflow. /review-security runs as Stage 2 when the diff touches security-sensitive code (auto-detected) or when --security is passed; skip with --no-security. Runs pre-landing code review, then live design audit, then QA testing — passing context forward between each stage. Use when you want the complete review pipeline in one command. Accepts optional URL, tier, and security flag arguments.

Architect mode — offload implementation to a watchable codex builder, judge results against frozen gates

Quick pre-merge safety check. Runs the critical-only pass from /review, a smoke-test QA (homepage + affected pages), and a quick test run. Designed for small PRs where /full-review is overkill. Use when asked to "preflight", "quick check", "safe to merge?", "sanity check", or "pre-merge check".

Emergency triage agent for production incidents and urgent bugs. Auto-invoked when the user says "this is broken", "production issue", "urgent fix", "hotfix", "incident", "prod is down", "critical bug", "emergency", "on-fire", or reports errors with urgency language. Routes to the appropriate workflow — /investigate for root cause, fast-track /review + /ship for the fix. Operates in emergency mode with streamlined processes.

Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.

Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Drive a goal to a merge-ready endpoint by orchestrating the offload architect loop: run contextual plan reviews, dispatch a codex builder slice-by-slice, wait for each slice via a backgrounded bridge (no Claude-side polling), judge raw gates plus an independent `review` pass per slice, and run a final integration `review`. STOPS at the edge of merge by default and hands to the human — only merges when the goal text explicitly authorizes it. You stay the ARCHITECT and never write implementation code. Use when the user says "complete", "drive this to done", "take this to merge-ready", "run the whole loop", or invokes /complete.

Use when assessing an idea, plan, strategy, product direction, public decision, creative concept, or proposal from multiple perspectives. Triggers: council, debate this, assess this idea, challenge my plan, stress-test, devil's advocate, ethical review, pragmatic next step, visionary take, creative reframing, pre-mortem, trade-offs, values alignment, long-term implications.

3 hooks across 2 events