Tons of Skills — Claude Code Plugins Marketplace
A unified catalog of 471 plugins, 3,179 skills, and 347 agents for Claude Code, with a CLI package manager.
- Source repo
- jeremylongshore/tons-of-skills-marketplace
- Stars
- ★ 2.9k
- Last updated
- today
- License
- MIT
- Primary language
- Python
- FA score
- 28/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specificClaude Code
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- Developers looking to extend Claude Code's capabilities by exploring 471 plugins across 19 categories.
- Not a fit if
- Teams using agent harnesses other than Claude Code; others are unverified
- Users who need fully offline browsing and install without tonsofskills.com
- Users expecting official support and quality guarantees for every plugin
- Source review
- 28/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
Tons of Skills is an open-source marketplace for Claude Code plugins, hosted on GitHub, offering 471 plugins, 3,179 skills, and 347 agents, all validated and ready to install. It provides a canonical catalog (marketplace.extended.json), enforced 8-field frontmatter standards, and automated validation against the AgentSkills.io spec. Users can install plugins via the ccpi CLI or Claude's built-in /plugin command. The repository also includes a public wiki, 11 production playbooks, and a learning lab to support large-scale deployments. All plugins target Anthropic's official Claude Code CLI.
The repository maintains a canonical plugin catalog (marketplace.extended.json) and includes the source for each plugin. It runs validations via scripts to ensure compliance with the AgentSkills.io spec and Claude Code's skills and plugins references. Users can search and install plugins using the ccpi CLI (e.g., ccpi search devops) or use Claude's built-in command /plugin marketplace add jeremylongshore/claude-code-plugins. The marketplace is browsable at tonsofskills.com, offering plugins, skills, and bundles. It also features a 'Killer Skill of the Week' spotlight, showcasing specific plugins like no-ai-slop and tonone.
- Developers looking to extend Claude Code's capabilities by exploring 471 plugins across 19 categories.
- DevOps engineers wanting to quickly install a packed suite like devops-automation-pack via the CLI.
- Developers building custom plugins or skills who want them validated and added to the marketplace.
- Users who prefer to download bundles from tonsofskills.com for team or project use.
- Teams managing multiple plugins and updates, leveraging the ccpi CLI for streamlined updates.
How do you install or deploy this agent?
Install the ccpi CLI globally via npm or pnpm: pnpm add -g @intentsolutionsio/ccpi. Alternatively, in Claude Code, add the marketplace using /plugin marketplace add jeremylongshore/claude-code-plugins.
How do you use this agent?
After installing the CLI, use ccpi search devops to search plugins by keyword, ccpi install devops-automation-pack to install a specific plugin, ccpi list --installed to see what's installed, and ccpi update to pull latest versions. Alternatively, use Claude's built-in commands to add the marketplace and install plugins, e.g., /plugin install devops-automation-pack@claude-code-plugins-plus.
What are this agent's strengths and limitations?
- Massive catalog: 471 plugins and 3,179 skills across broad categories.
- Enforced validation: All plugins are automatically validated for spec compliance, ensuring quality.
- Easy CLI and Claude integration simplifies installation and updates.
- Production-grade documentation: Includes wiki, playbooks, and learning lab.
- Claude Code-only: Built exclusively for Anthropic's CLI, not compatible with other AI agents.
- Requires Node and a package manager (pnpm or npm).
- Relies on external site tonsofskills.com for browsing and installation.
- Variable plugin quality: Some plugins may be community-contributed with limited support.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Tons of Skills — Claude Code Plugins Marketplace This agent | 28 · Major gaps | Agent plugin / skillFree | ★ 2.9k | today | Python | Claude Code |
| AI DevOps Framework (aidevops) | 65 · Some gaps | CLIFree + model costs | ★ 411 | today | Shell | OpenAI API · Claude API |
| DevOps AI Guidelines & Learning Path | 25 · Major gaps | Library / SDKFree | ★ 1.6k | 25d ago | Python | — |
| Agent Reach | 62 · Some gaps | CLIFree | ★ 99k | 11d ago | Python | Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The evidence shows a repository with many plugins and skills, but no specific information on least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, or source attribution. All trust criteria are unsupported, hence scored 0.
The repository shows validation scripts and tests, but insufficient evidence for self-consistency, dependency availability, or failure messages. Self-consistency scored 1 due to presence of validation and tests, but not deeply verified. Dependency availability scored 1 as npm packages are listed but availability not verified. Failure messages scored 0 as no evidence provided.
The repository targets Claude Code users, offering plugins and skills for various scenarios, but evidence for capability boundaries, trigger precision, and environment fit is thin. Audience and scenarios scored 2 due to categorization and descriptions. Capability boundaries scored 1 as limitations not clearly stated. Trigger precision scored 1 as no details on triggers. Environment fit scored 1 as only Claude Code mentioned.
Information architecture is clear with categories and index, scored 2. Install notes are detailed, scored 2. Naming stability not explicit, scored 1. Examples and FAQ limited, scored 1. Known limitations not mentioned, scored 0. License is MIT, scored 2. Versioning and changelog have version number but no detailed log, scored 1. Maintenance responsibility by author but not explicit, scored 1.
Output usability not explicit, scored 1. Marginal value high due to large number of plugins and skills, scored 2. Cost-benefit not explicit, scored 1.
Claim traceability limited, scored 1. Cross-source corroboration limited, scored 1. Fact-inference separation insufficient, scored 1.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- The repository contains many third-party plugins and skills, but no security audit or least privilege evidence is provided; evaluate carefully before installation.
- No user confirmation or data flow transparency mechanisms are provided; may involve sensitive data handling, requiring further review.
- Dependency security is not explicit, posing supply chain risks; check dependency sources and versions.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Released by publish-changed-packages.yml on push to main. npm: https://www.npmjs.com/package/@intentsolutionsio/intent-labs-pack/v/0.1.0 Source: plugins/productivity/intent-labs-pack Install: pnpm add @intentsolutionsio/[email protected] (or /plugin install via Claude Code marketplace) What's Changed * fix(catalog): repair SKILL.md drift + 3 downgrades, make --check verify all surfaces [skip auto-bump] by @jeremylongshore in https://github.com/jeremylongshore/claude-code-plugins-plus-skills/pull/1098 …View on GitHub ↗ -
Release notes excerpt
Released by publish-changed-packages.yml on push to main. npm: https://www.npmjs.com/package/@intentsolutionsio/freshie-inventory-manager/v/1.1.0 Source: plugins/database/freshie-inventory-manager Install: pnpm add @intentsolutionsio/[email protected] (or /plugin install via Claude Code marketplace) What's Changed * 📦 Daily npm download stats refresh by @github-actions[bot] in https://github.com/jeremylongshore/claude-code-plugins-plus-skills/pull/1094 …View on GitHub ↗ -
Release notes excerpt
Released by publish-changed-packages.yml on push to main. npm: https://www.npmjs.com/package/@intentsolutionsio/clerk-pack/v/1.0.4 Source: plugins/saas-packs/clerk-pack Install: pnpm add @intentsolutionsio/[email protected] (or /plugin install via Claude Code marketplace) What's Changed * fix(clerk-pack): update Clerk pricing to current 50k MRU model by @astrotars in https://github.com/jeremylongshore/claude-code-plugins-plus-skills/pull/1081 New Contributors …View on GitHub ↗
FAQ
Is the ccpi CLI free?
Can I contribute my own plugins?
What if a plugin is not compatible?
How do updates work?
ccpi update command to pull latest versions.