Quality

H-Diagnose stabilizes a concrete failure, generates distinct rival explanations, tests discriminating observations read-only in parallel, and ranks them by evidence while retaining losing hypotheses for later use.

H Verify compares recorded DecisionRecords or claims against current code, tests, measurements, or incidents to surface weakened, refuted, stale, or drifted claims. Use it when design-time claims need runtime evidence before relying on them.

Audit Env Variables scans JavaScript/TypeScript projects for environment variable usage, identifies unused or undeclared variables, detects services like Stripe, AWS, and Supabase, and generates a structured markdown report. Use it to review security, document configuration, or clean up unused variables with regression detection.

Remove Dead Code safely identifies and removes dead code in TypeScript/JavaScript projects using multi-agent analysis with automatic backup branches. Use when cleaning up unused exports, orphaned files, dead imports, unreachable functions, or unused dependencies.

Auto Review runs a structured pre-commit/ship code review with a bundled helper, defaulting to Codex (gpt-5.6-sol) and optionally Claude or Pi. Use it after non-trivial code edits or when asked for autoreview/second-model review to catch actionable findings before merging.

Verify drives an engine app headlessly in a pty, records a video of the entire verification run, and opens a summary page with video, timeline, and pass/fail checks. Use it to verify terminal apps that render via the kitty graphics protocol and capture every frame with input overlays.

Guides German notaries in drafting and reviewing marriage contracts, divorce agreements, and pension equalization clauses. Assesses formal requirements, deadlines, and risks, and produces structured checklists and client communications.

Reviews debt collection lawsuit drafts from the defendant's perspective, identifying weaknesses in legitimacy, evidence, and timelines. Provides a risk assessment and immediate action steps.

Accessibility Audit generates a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use it when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan.

Helmor Debug Loop drives a bounded reproduce, instrument, inspect, fix, and verify cycle for Helmor local development bugs. Use it when an agent must diagnose and fix issues in the Helmor desktop app using Tauri MCP, logs, screenshots, and IPC traces.

AutoContext uses LLM-based judging with rubric-driven scoring to evaluate and improve agent outputs. Use it to run improvement loops, queue background evaluations, check run status, inspect artifacts and session lineage, or discover scenarios.

Audit Content verifies truthfulness, accuracy, and link integrity of content before publishing. It catches fabricated statistics, dead URLs, misattributed sources, and company claims that contradict the brand DNA.