Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 387,436 indexed, measured the same four ways as everything else here.
A writing guide for maintaining a CHANGELOG.md file, which records user-visible changes between software versions. It also covers the release notes taken from the current version section.
MCP server "aider-mcp-server" as configured in disler/aider-mcp-server. Launched with uv --directory . run aider-mcp-server --editor-model gemini/gemini-2.5-pro-previ.
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…
MCP server "domain-check" as configured in saidutt46/domain-check. Launched with https://github.com/saidutt46/domain-check/releases/download/v1.2.1/domain-check-.
★not rated 308▲
+2
changed 13d agoA
tokens not measured
Production hardening for AI coding agents — quality gates, security guards, continuous QA, and session memory. From the LACP (Local Agent Control Plane) framework.
★not rated 308▲
+1 13d agoA
tokens not measured
originalMIT
Operate FLVX traffic forwarding management system via REST API. Supports user/node/tunnel/forward management, federation clustering, and traffic monitoring. Use when user wants to manage FLVX panel programmatically or via natural language.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
★not rated 308 yesterdayA
tokens not measured
AGPL-3.0
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
Extracts structured data from websites and APIs, delivering clean datasets in multiple formats. Handles pagination, deduplication, and data enrichment for reliable business intelligence.
Concrete UI visual rule set for generating and reviewing restrained neutral interfaces. Use for tasks that need exact style constraints: plain sans-serif typography, pale neutral canvases, rounded surfaces, soft shadows, minimal borders, low-saturation color, sparse density, content-neutral placeholders, and…
Use when writing, testing, or preparing ANY contribution or pull request to the JSONbored/awesome-claude (HeyClaude) repo — adding a community content entry (agent/MCP server/skill/hook/command/rule/guide/collection/statusline), or making a platform/code change (website, registry package, MCP package, scripts). The…
Use when building a new agent harness, designing tool systems, or structuring multi-agent workflows. Provides patterns, templates, and decision trees for harness engineering.
Guardrails for Claude Code: the rules that fit the task delivered per prompt, and no risky writes before you approve a plan and tests. Hybrid retrieval (BM25 + vector + graph traversal + weighted ranking, with an abstention gate) over a Neo4j knowledge graph, wired in through hook scripts and a session state machine.
Discover prior agent work across sessions, projects, providers, and machines. Use for historical investigations and analogous solutions, or as a fallback when native conversation and history tools cannot recover the needed evidence.
Keep AI slop out of your prose and your repo: a merged humanizer skill (41 patterns), voice calibration, repo auditing, and a zero-dependency slop scanner with CI gating.
A document-handling skill for HWP and HWPX, file formats used by Hancom Hangul, a Korean word processor. It can create, read, edit, and convert these documents, including turning HTML worksheets into editable HWPX files.
A skill for giving tarot readings in Chinese, including card draws, upright or reversed cards, and spreads. It covers topics such as relationships, work, decisions, and daily guidance.
★not rated 311▲
+10 5mo agoA63 tokens
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: