claw-mo

Complete Claude Code plugin marketplace — agents, skills, hooks, commands, rules, MCPs.

Replaces Claude Code's built-in worktree — aligns with native git worktree where CC diverges (HEAD base, origin/* auto-tracking) and adds layers native lacks: .worktreeinclude/.worktreelink for gitignored files with a /worktree-setup skill that scans and builds them, upstream-aware removal guard, idempotent re-entry.

State-aware VibeProxy alias manager for Claude Code. Discover VibeProxy state, choose backend-specific cc-* aliases, and rewrite only managed config and shell blocks without clobbering manual edits.

Create, test, and iteratively improve Claude Code skills with the official lean coaching loop, an eval harness for benchmarking with variance analysis, and automated description-trigger optimization

Analyze Claude Code plugins and visualize development artifacts as interactive HTML or diagram-enhanced markdown reports. On a capable account, HTML reports publish as claude.ai Artifacts by default (doc-visual, diff-visual, plugin-visual, context-health-visual); add --local for a local design-system + Mermaid file. Six skills: plugin-visual (local/installed/GitHub plugin audits with security + architecture), diff-visual (git diffs, with side-by-side split-diff of the actual changed code and File Map change-flags), doc-visual (markdown docs with Mermaid diagrams), fact-check (claim verification against code + git history, republishing corrections to the same Artifact link), context-health-visual (environment health with skill-security scan and hook schema validation), report-manager (list/open/delete/search/refine, surfacing stored Artifact URLs and republishing to the same link). Every report supports --format md, --lang, and in-browser per-section feedback.

A plugin to manage NotebookLM notebooks and query them using integrated features.

cmux terminal integration: terminal I/O, topology control, browser automation, markdown viewer, notifications

Get Codex's second opinion — and actually trust it: a different model reviews your code, plans, and research, and Claude fact-checks every finding (Agreed/Disputed/Nuanced/False Positive/Uncited) before you act, catching hallucinated citations. Skills: setup, review, adversarial, rescue, verify, research, status, result, cancel, transfer. Task delegation (rescue) wraps your verbatim request in adaptive, preview-approved prompt blocks. Transfer hands the whole session off to a resumable Codex thread (v1.0.5+). Prompt-running skills accept --model/--effort via config.toml.

Run E2E browser tests using natural language test definitions powered by Claude Code SDK and agent-browser with video recording

Rubber duck tutor that keeps you engaged across the whole AI-coding lifecycle — before you ask AI to build (/duck-prebuild), once code is written and before you ship (/duck-verify, /duck-review), and when orienting to unfamiliar code (/duck-orient), plus /duck for auto-detect. /coach is its teaching sibling, manual-invocation only: /coach <topic> explains and drills a concept, /coach <file> or a bare /coach right after generating code dissects it section by section (what/why-this-way/where-it-breaks), and /coach alone surfaces an unresolved gap from a past duck session and teaches it — resolved only once you pass the exercise, not by saying you understand. Ship-point hooks triage what you just pushed against six risk categories and target the riskiest change you didn't actually discuss, fall back to retrieving an unresolved gap from a past session, or demote to a non-blocking scoreboard after three ignored confrontations in a row. Confrontation telemetry (fired/answered/ignored) is queryable from /duck-orient. Doesn't overlap /code-review or /grilling — duck only checks whether you understand, never whether the code or plan is good, and never teaches — that's coach's job.