Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,536 indexed, measured the same four ways as everything else here.
Everything you need to design, build, and document AI workflows. The AI Workflow Framework as executable skills, plus your business knowledge graph, an AI registry, and a feature-spec toolkit.
★not rated 8
changed 2d agoA
tokens not measured
originalMIT
Use this agent when code has been written or modified and needs a thorough review for quality, correctness, security, performance, and maintainability. Trigger this agent after completing a logical chunk of work such as a new feature, bug fix, or refactor.\n\n \nContext: The user has just written a new authentication…
skraft SDLC pipeline — agents, skills and instructions for outside-in TDD, Clean Architecture, backlog discovery and the RESEARCH→DESIGN→DISTILL→DELIVER engineering pipeline.
★not rated 8
changed yesterdayA
tokens not measured
GPL-3.0
Java + Spring Boot TDD workflow plugin with requirements input drafting, RGB cycle, feature-level autonomous implementation, Cucumber acceptance testing, local tidying, system-wide refactoring, and 18 optional refactoring skills. Plan phase and Web App acceptance/skeleton setup now delegate to dedicated agents instead.
★not rated 8
changed 16d agoA
tokens not measured
originalMIT
Configure a custom status line for Claude Code to display contextual information like model name, directory, and git branch at the bottom of the interface.
Adversarial cross-examiner mode. Claude plays opposing counsel — one substantive objection per turn, no approval until every objection is answered. Counters the 'Claude is too agreeable' failure mode by design.
★not rated 8 5mo agoA
tokens not measured
originalMIT
Orchestrate plan reviews, task generation, implementation, and code reviews in parallel across 13 coding harnesses (Codex, Cursor, opencode, pi, aider, Antigravity…) — or ask every model a free-text question about a plan.
★not rated 8 2mo agoA
tokens not measured
originalMIT
A First Principles-based technical learning plugin. Multi-source research and study (PDF, URL, GitHub), structured note generation, Slack daily quizzes, technical blog writing with Notion integration, and Docker lab environments.
★not rated 8 7mo agoA
tokens not measured
originalMIT
Automated code review enforcement. Runs autofix, architecture verification, and conversation review -- and blocks sessions from finishing until they pass.
A set of strict CSS and React component guidelines for replicating the highly dense, micro-indexed, and smoothly expanding auto-hiding scrollbar side panel UI seen in DeepSeek's chat history timeline.
Build a source-backed GTM Brain for your company with specialist agents, skills, Grill-me questions, MVP checklists, and session handoffs. Originally built for Freckle.io's company GTM brain, then repurposed into a public plugin anyone can use.
★not rated 8 5mo agoA
tokens not measured
originalMIT
Learn how to inspect and operate Nokia SR network OSes - SR OS (SROS) and SR Linux (SRL): tell the two apart, fetch YANG models on demand, read the software version, understand config formats, and apply NETCONF / MD-CLI / gNMI behaviors.
★not rated 8
changed yesterdayA
tokens not measured
originalMIT
Use after any user request that might entail more than a single tool call or anything more than quick, shallow thinking. This surfaces relevant memories that are VITAL to recall for a good user experience and a greater chance at first-pass success for the user's request.
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: