MCP server Claude CodeCodexCursor +2
MCP server "claude-code-docs", hosted remotely at code.claude.com, as configured in bengous/claude-code-plugins.
not rated 5 today A
tokens not measured
original MIT
Plugin Claude Code
Bundles 6 skills · 445 tokens together
Bridge to the OpenAI Codex CLI for cross-model collaboration.
not rated 5
changed 9d ago A
tokens not measured
original MIT
Agent Claude Code
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
not rated 5 today A 50 tokens
original MIT
Agent Claude Code
Read-only auditor for silent error swallowing in Effect code. Receives scanner JSON, reads source context, classifies severity, prescribes fixes. Spawned by /null-as-error skill.
not rated 5 today A 44 tokens
original MIT
Agent Claude Code
Read-only infrastructure code auditor for /refactorlib. Searches for handcrafted infrastructure code (HTTP, retry, scheduling, platform I/O, CLI, config, concurrency) replaceable by installed library APIs. Use when /refactorlib spawns parallel exploration.
not rated 5 today A 57 tokens
original MIT
Agent Claude Code
Read-only utility code auditor for /refactorlib. Searches for handcrafted utility code (string, date, collections, ID generation, encoding, URL parsing, deep clone) replaceable by installed library APIs or native APIs. Use when /refactorlib spawns parallel exploration.
not rated 5 today A 61 tokens
copy · 86% MIT
Command Claude Code
Invoke the null-as-error skill to audit the current project for silent error swallowing in Effect code.
not rated 5 today A 0 tokens
original MIT
Skill Claude Code
Audit an Effect codebase for silent error swallowing -- catchAll patterns that collapse errors into sentinel values (null, [], false, void) in the success channel. Runs a scanner script, spawns a read-only auditor, and produces a classified report. NOT for: non-Effect projects, React/frontend code, plain TypeScript…
not rated 5 today A 74 tokens
original MIT
Skill Claude Code
Audit a codebase for handcrafted code that duplicates functionality already available in the project's dependencies. Reads package.json, launches parallel exploration agents, verifies replacement feasibility, and produces a structured refactor plan. Audit only -- does not execute changes.
not rated 5 today A 52 tokens
original MIT
analyze-git
10Command Claude Code
Perform a comprehensive analysis of the git repository to identify branches and worktrees that can be cleaned up. This is a READ-ONLY analysis - no deletions will be performed.
not rated 5 today A 0 tokens
original MIT
cleanup-git
11Command Claude Code
Perform git repository cleanup operations based on the analysis from /git-tools:analyze-git.
not rated 5 today A 0 tokens
original MIT
plan-with-wt
12Command Claude Code
Approve plan mode with worktree isolation and PR creation.
not rated 5 today A 10 tokens
original MIT
plan-review
13Plugin Claude Code
Bundles 1 command, 1 agent · 24 tokens together
Multi-agent plan review workflow requiring architect and simplifier approval before plan execution.
not rated 5 today A
tokens not measured
original MIT
Skill Claude CodeCodex
Rigorous planning workflow with research validation, task breakdown, dependency mapping, and post-implementation verification. Use when: (1) planning complex features touching 5+ files, (2) architectural changes or major refactors, (3) unfamiliar tech requiring doc research, (4) user says "thorough plan", "rigorous…
not rated 5 today A 88 tokens
original MIT
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
not rated 5 today A 45 tokens
copy · 88% MIT
Plugin Claude Code
Bundles 1 skill · 69 tokens together
Meta tooling for Claude Code: write prompts that prompt better (meta-prompt).
not rated 5
changed 1mo ago A
tokens not measured
original MIT
Plugin Claude Code
Bundles 2 commands · 16 tokens together
Manage Claude Code settings with JSONC support and schema extraction.
not rated 5
changed 24d ago A
tokens not measured
original MIT
Plugin Claude Code
Bundles 1 skill, 1 agent · 176 tokens together
Audit and clean code comments: protects why/constraint comments, hunts comments that lie.
not rated 5 today A
tokens not measured
original MIT
code-quality
19Plugin Claude Code
Bundles 1 skill, 2 commands · 83 tokens together
Code quality and cleanup commands for maintaining clean, maintainable code.
not rated 5
changed 24d ago A
tokens not measured
original MIT
Plugin Claude Code
Bundles 3 skills · 123 tokens together
Lifecycle of Claude Code instruction files: audit CLAUDE.md/AGENTS.md/.claude/rules instruction budget, capture session learnings, and resync docs with codebase evolution.
not rated 5
changed 24d ago A
tokens not measured
original MIT
Plugin Claude Code
Bundles 1 agent · 14 tokens together
Generate 5 unique website redesigns using Theo's pattern: one agent, sequential creation, natural differentiation.
not rated 5
changed 24d ago A
tokens not measured
original MIT
git-sweep
22Plugin Claude Code
Bundles 1 skill · 76 tokens together
Interactive git branch and worktree cleanup: proves a branch is contained before proposing it, frees finished worktrees, and reports what it kept and why.
not rated 5
changed 21d ago A
tokens not measured
original MIT
ship
23Plugin Claude Code
Bundles 1 skill · 81 tokens together
Ship feature branches: strip working files, create PRs, merge to main with GPG signing and squash support.
not rated 5 today A
tokens not measured
original MIT
git-worktree
24Plugin Claude Code
Bundles 1 command · 12 tokens together
Git worktree helper with stack support for multi-agent orchestration.
not rated 5
changed 24d ago A
tokens not measured
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: