Compare commits

..

1 Commits

Author SHA1 Message Date
Dickson Tsai
f227eeb90c Add version field to 27 local-sourced plugins
Local-path plugins (source is a string like "./plugins/foo" in
marketplace.json) without a manifest version cache at
~/.claude/plugins/cache/{marketplace}/{plugin}/unknown/ forever.

The cache check in claude-cli's copyPluginToVersionedCache sees
pathExists(.../unknown/) → true → skips re-extraction, even after
the marketplace content updates. Users are stuck with stale plugin
files until they manually delete the cache.

Adding "version": "1.0.0" fixes this because calculatePluginVersion
reads the manifest from the freshly-synced marketplace tree (not the
stale cache), and manifest.version is priority #1 in version
resolution. New version → new cache path → cache miss → re-extract.

This is preferable to the GCS-SHA fallback approach
(anthropics/claude-cli-internal#24773) because:
- Per-plugin granularity: only bumped plugins re-extract, not all
  27 on every marketplace push
- No disk accumulation from unrelated marketplace churn
- Fixes both the runtime loader path AND the migration path
  (manifest.version is priority #1 in both)
- No claude-cli code change needed

Remote-sourced plugins (github/git/url) already get a git SHA as
their version and are unaffected.
2026-03-26 22:02:14 -07:00
28 changed files with 50 additions and 45 deletions

View File

@@ -53,7 +53,7 @@
},
{
"name": "aikido",
"description": "Aikido Security scanning for Claude Code \u2014 SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.",
"description": "Aikido Security scanning for Claude Code SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.",
"source": {
"source": "url",
"url": "https://github.com/AikidoSec/aikido-claude-plugin.git",
@@ -243,7 +243,7 @@
},
{
"name": "cockroachdb",
"description": "CockroachDB plugin for Claude Code \u2014 explore schemas, write optimized SQL, debug queries, and manage distributed database clusters directly from your AI coding agent.",
"description": "CockroachDB plugin for Claude Code explore schemas, write optimized SQL, debug queries, and manage distributed database clusters directly from your AI coding agent.",
"source": {
"source": "url",
"url": "https://github.com/cockroachdb/claude-plugin.git",
@@ -275,7 +275,7 @@
},
{
"name": "coderabbit",
"description": "Your code review partner. CodeRabbit provides external validation using a specialized AI architecture and 40+ integrated static analyzers\u2014offering a different perspective that catches bugs, security vulnerabilities, logic errors, and edge cases. Context-aware analysis via AST parsing and codegraph relationships. Automatically incorporates CLAUDE.md and project coding guidelines into reviews. Useful after writing or modifying code, before commits, when implementing complex or security-sensitive logic, or when a second opinion would increase confidence in the changes. Returns specific findings with suggested fixes that can be applied immediately. Free to use.",
"description": "Your code review partner. CodeRabbit provides external validation using a specialized AI architecture and 40+ integrated static analyzersoffering a different perspective that catches bugs, security vulnerabilities, logic errors, and edge cases. Context-aware analysis via AST parsing and codegraph relationships. Automatically incorporates CLAUDE.md and project coding guidelines into reviews. Useful after writing or modifying code, before commits, when implementing complex or security-sensitive logic, or when a second opinion would increase confidence in the changes. Returns specific findings with suggested fixes that can be applied immediately. Free to use.",
"category": "productivity",
"source": {
"source": "url",
@@ -365,7 +365,7 @@
},
{
"name": "elixir-ls-lsp",
"description": "Elixir language server (ElixirLS) for Claude Code \u2014 provides code intelligence and diagnostics for .ex, .exs, and .heex files.",
"description": "Elixir language server (ElixirLS) for Claude Code provides code intelligence and diagnostics for .ex, .exs, and .heex files.",
"source": {
"source": "url",
"url": "https://github.com/MikaelFangel/claude-elixir-ls-lsp.git",
@@ -464,7 +464,7 @@
"source": {
"source": "url",
"url": "https://github.com/tryflint/claude-code-plugin.git",
"sha": "f3d56e33ed2fb3ed9b4f02e0fc65d0a79b24bf4d"
"sha": "8f57ef474f59817c7e5930dd6c295232d43c3711"
},
"homepage": "https://www.tryflint.com/docs/claude-code-plugin"
},
@@ -542,7 +542,7 @@
},
{
"name": "helius",
"description": "Build on Solana with Helius \u2014 live blockchain tools, expert coding patterns, and autonomous account signup",
"description": "Build on Solana with Helius live blockchain tools, expert coding patterns, and autonomous account signup",
"source": {
"source": "git-subdir",
"url": "helius-labs/core-ai",
@@ -753,7 +753,7 @@
},
{
"name": "netlify-skills",
"description": "Netlify platform skills for Claude Code \u2014 functions, edge functions, blobs, database, image CDN, forms, config, CLI, frameworks, caching, AI gateway, and deployment.",
"description": "Netlify platform skills for Claude Code functions, edge functions, blobs, database, image CDN, forms, config, CLI, frameworks, caching, AI gateway, and deployment.",
"category": "development",
"source": {
"source": "url",
@@ -773,7 +773,7 @@
},
{
"name": "nimble",
"description": "Nimble web data toolkit \u2014 search, extract, map, crawl the web and work with structured data agents",
"description": "Nimble web data toolkit search, extract, map, crawl the web and work with structured data agents",
"source": {
"source": "url",
"url": "https://github.com/Nimbleway/agent-skills.git",
@@ -793,7 +793,7 @@
},
{
"name": "opsera-devsecops",
"description": "Opsera DevSecOps Agent \u2014 AI-powered architecture analysis, security scanning, compliance auditing, and SQL security for your codebase. Free trial included.",
"description": "Opsera DevSecOps Agent AI-powered architecture analysis, security scanning, compliance auditing, and SQL security for your codebase. Free trial included.",
"source": {
"source": "url",
"url": "https://github.com/opsera-agents/opsera-devsecops.git",
@@ -803,7 +803,7 @@
},
{
"name": "optibot",
"description": "AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities \u2014 directly in Claude Code.",
"description": "AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities directly in Claude Code.",
"source": {
"source": "url",
"url": "https://github.com/Optimal-AI/optibot-skill.git",
@@ -868,7 +868,7 @@
},
{
"name": "playground",
"description": "Creates interactive HTML playgrounds \u2014 self-contained single-file explorers with visual controls, live preview, and prompt output with copy button. Includes templates for design playgrounds, data explorers, concept maps, and document critique.",
"description": "Creates interactive HTML playgrounds self-contained single-file explorers with visual controls, live preview, and prompt output with copy button. Includes templates for design playgrounds, data explorers, concept maps, and document critique.",
"author": {
"name": "Anthropic",
"email": "support@anthropic.com"
@@ -950,7 +950,7 @@
},
{
"name": "product-tracking-skills",
"description": "AI agent skills that make SaaS products data-ready for product analytics \u2014 from codebase scan to tracking plan to working instrumentation code.",
"description": "AI agent skills that make SaaS products data-ready for product analytics from codebase scan to tracking plan to working instrumentation code.",
"source": {
"source": "url",
"url": "https://github.com/Accoil/product-tracking-skills.git",
@@ -984,7 +984,7 @@
},
{
"name": "qodo-skills",
"description": "Qodo Skills provides a curated library of reusable AI agent capabilities that extend Claude's functionality for software development workflows. Each skill is designed to integrate seamlessly into your development process, enabling tasks like code quality checks, automated testing, security scanning, and compliance validation. Skills operate across your entire SDLC\u2014from IDE to CI/CD\u2014ensuring consistent standards and catching issues early.",
"description": "Qodo Skills provides a curated library of reusable AI agent capabilities that extend Claude's functionality for software development workflows. Each skill is designed to integrate seamlessly into your development process, enabling tasks like code quality checks, automated testing, security scanning, and compliance validation. Skills operate across your entire SDLCfrom IDE to CI/CDensuring consistent standards and catching issues early.",
"category": "development",
"source": {
"source": "url",
@@ -1108,7 +1108,7 @@
},
{
"name": "searchfit-seo",
"description": "Free AI-powered SEO toolkit \u2014 audit websites, plan content strategy, optimize pages, generate schema markup, cluster keywords, and track AI visibility. Works with any website or codebase.",
"description": "Free AI-powered SEO toolkit audit websites, plan content strategy, optimize pages, generate schema markup, cluster keywords, and track AI visibility. Works with any website or codebase.",
"source": {
"source": "url",
"url": "https://github.com/searchfit/searchfit-seo.git",
@@ -1331,32 +1331,6 @@
}
}
},
{
"name": "ui5",
"description": "SAPUI5 / OpenUI5 plugin for Claude. Create and validate UI5 projects, access API documentation, run UI5 linter, get development guidelines and best practices for UI5 development.",
"category": "development",
"source": {
"source": "git-subdir",
"url": "UI5/plugins-claude",
"path": "plugins/ui5",
"ref": "main",
"sha": "5070dfc1cef711d6efad40beb43750027039d71f"
},
"homepage": "https://github.com/UI5/plugins-claude"
},
{
"name": "ui5-typescript-conversion",
"description": "SAPUI5 / OpenUI5 plugin for Claude. Convert JavaScript based UI5 projects to TypeScript.",
"category": "development",
"source": {
"source": "git-subdir",
"url": "UI5/plugins-claude",
"path": "plugins/ui5-typescript-conversion",
"ref": "main",
"sha": "5070dfc1cef711d6efad40beb43750027039d71f"
},
"homepage": "https://github.com/UI5/plugins-claude"
},
{
"name": "vercel",
"description": "Vercel deployment platform integration. Manage deployments, check build status, access logs, configure domains, and control your frontend infrastructure directly from Claude Code.",

View File

@@ -1,5 +1,6 @@
{
"name": "asana",
"version": "1.0.0",
"description": "Asana project management integration. Create and manage tasks, search projects, update assignments, track progress, and integrate your development workflow with Asana's work management platform.",
"author": {
"name": "Asana"

View File

@@ -1,5 +1,6 @@
{
"name": "context7",
"version": "1.0.0",
"description": "Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.",
"author": {
"name": "Upstash"

View File

@@ -1,5 +1,6 @@
{
"name": "firebase",
"version": "1.0.0",
"description": "Google Firebase MCP integration. Manage Firestore databases, authentication, cloud functions, hosting, and storage. Build and manage your Firebase backend directly from your development workflow.",
"author": {
"name": "Google"

View File

@@ -1,5 +1,6 @@
{
"name": "github",
"version": "1.0.0",
"description": "Official GitHub MCP server for repository management. Create issues, manage pull requests, review code, search repositories, and interact with GitHub's full API directly from Claude Code.",
"author": {
"name": "GitHub"

View File

@@ -1,5 +1,6 @@
{
"name": "gitlab",
"version": "1.0.0",
"description": "GitLab DevOps platform integration. Manage repositories, merge requests, CI/CD pipelines, issues, and wikis. Full access to GitLab's comprehensive DevOps lifecycle tools.",
"author": {
"name": "GitLab"

View File

@@ -1,10 +1,17 @@
{
"name": "greptile",
"version": "1.0.0",
"description": "AI code review agent for GitHub and GitLab. View and resolve Greptile's PR review comments directly from Claude Code.",
"author": {
"name": "Greptile",
"url": "https://greptile.com"
},
"homepage": "https://greptile.com/docs",
"keywords": ["code-review", "pull-requests", "github", "gitlab", "ai"]
"keywords": [
"code-review",
"pull-requests",
"github",
"gitlab",
"ai"
]
}

View File

@@ -1,5 +1,6 @@
{
"name": "laravel-boost",
"version": "1.0.0",
"description": "Laravel development toolkit MCP server. Provides intelligent assistance for Laravel applications including Artisan commands, Eloquent queries, routing, migrations, and framework-specific code generation.",
"author": {
"name": "Laravel"

View File

@@ -1,5 +1,6 @@
{
"name": "linear",
"version": "1.0.0",
"description": "Linear issue tracking integration. Create issues, manage projects, update statuses, search across workspaces, and streamline your software development workflow with Linear's modern issue tracker.",
"author": {
"name": "Linear"

View File

@@ -1,5 +1,6 @@
{
"name": "playwright",
"version": "1.0.0",
"description": "Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.",
"author": {
"name": "Microsoft"

View File

@@ -1,5 +1,6 @@
{
"name": "serena",
"version": "1.0.0",
"description": "Semantic code analysis MCP server providing intelligent code understanding, refactoring suggestions, and codebase navigation through language server protocol integration.",
"author": {
"name": "Oraios"

View File

@@ -1,5 +1,6 @@
{
"name": "supabase",
"version": "1.0.0",
"description": "Supabase MCP integration for database operations, authentication, storage, and real-time subscriptions. Manage your Supabase projects, run SQL queries, and interact with your backend directly.",
"author": {
"name": "Supabase"

View File

@@ -1,5 +1,6 @@
{
"name": "terraform",
"version": "1.0.0",
"description": "The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.",
"author": {
"name": "HashiCorp"

View File

@@ -1,5 +1,6 @@
{
"name": "agent-sdk-dev",
"version": "1.0.0",
"description": "Claude Agent SDK Development Plugin",
"author": {
"name": "Anthropic",

View File

@@ -1,9 +1,9 @@
{
"name": "code-review",
"version": "1.0.0",
"description": "Automated code review for pull requests using multiple specialized agents with confidence-based scoring",
"author": {
"name": "Anthropic",
"email": "support@anthropic.com"
}
}

View File

@@ -1,9 +1,9 @@
{
"name": "commit-commands",
"version": "1.0.0",
"description": "Streamline your git workflow with simple commands for committing, pushing, and creating pull requests",
"author": {
"name": "Anthropic",
"email": "support@anthropic.com"
}
}

View File

@@ -1,5 +1,6 @@
{
"name": "explanatory-output-style",
"version": "1.0.0",
"description": "Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "feature-dev",
"version": "1.0.0",
"description": "Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "frontend-design",
"version": "1.0.0",
"description": "Frontend design skill for UI/UX implementation",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "hookify",
"version": "1.0.0",
"description": "Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "learning-output-style",
"version": "1.0.0",
"description": "Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)",
"author": {
"name": "Anthropic",

View File

@@ -1,6 +1,7 @@
{
"name": "mcp-server-dev",
"description": "Skills for designing and building MCP servers that work seamlessly with Claude — guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.",
"version": "1.0.0",
"description": "Skills for designing and building MCP servers that work seamlessly with Claude \u2014 guides you through deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.",
"author": {
"name": "Anthropic",
"email": "support@anthropic.com"

View File

@@ -1,6 +1,7 @@
{
"name": "playground",
"description": "Creates interactive HTML playgrounds — self-contained single-file explorers with visual controls, live preview, and prompt output with copy button",
"version": "1.0.0",
"description": "Creates interactive HTML playgrounds \u2014 self-contained single-file explorers with visual controls, live preview, and prompt output with copy button",
"author": {
"name": "Anthropic",
"email": "support@anthropic.com"

View File

@@ -1,5 +1,6 @@
{
"name": "plugin-dev",
"version": "1.0.0",
"description": "Plugin development toolkit with skills for creating agents, commands, hooks, MCP integrations, and comprehensive plugin structure guidance",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "pr-review-toolkit",
"version": "1.0.0",
"description": "Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "ralph-loop",
"version": "1.0.0",
"description": "Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "security-guidance",
"version": "1.0.0",
"description": "Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns",
"author": {
"name": "Anthropic",

View File

@@ -1,5 +1,6 @@
{
"name": "skill-creator",
"version": "1.0.0",
"description": "Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.",
"author": {
"name": "Anthropic",