# claude-code-plugins-plus-skills

> 423 plugins, 2,849 skills, 177 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.

- **URL**: https://www.freshcrate.ai/projects/claude-code-plugins-plus-skills
- **Author**: jeremylongshore
- **Category**: MCP Servers
- **Latest version**: `v4.33.0` (2026-05-26)
- **License**: MIT
- **Source**: https://github.com/jeremylongshore/claude-code-plugins-plus-skills
- **Homepage**: https://tonsofskills.com
- **Language**: Python
- **GitHub**: 1,995 stars, 268 forks
- **Registry**: github (`jeremylongshore/claude-code-plugins-plus-skills`)
- **Tags**: `agent-skills`, `ai`, `ai-agents`, `anthropic`, `automation`, `claude-code`, `claude-code-plugins`, `developer-tools`, `mcp`, `python`

## Description

423 plugins, 2,849 skills, 177 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v4.33.0` | 2026-05-26 | High | Cowork pipeline correctness pass — the `/cowork/` page is now a deterministic function of the catalog from disk through deploy, with a CI gate that fails the build if anyone regresses the contract. Plus the agency-os plugin lands, a new Unicode hygiene CI gate hardens contributor PRs against [Trojan Source](https://trojansource.codes/) attacks (CVE-2021-42574), and the `/cowork/` page itself gets the prereq banner + setup-guide rewrite that users have been missing.  ### Added  - **agency-os plu |
| `v4.32.0` | 2026-05-24 | High | Single-session CI hardening campaign. Took `main` from 2 required CI gates to 10 across 9 sequential PRs (#763 through #772), with underlying violations fixed in-PR — no report-only crutch left in the pipeline.  ## 10 blocking required gates on `main`  \| Gate \| Source \| \|---\|---\| \| `validate` \| pre-existing (now includes widened-test-loop matrix) \| \| `marketplace-validation` \| pre-existing \| \| `eslint-check` \| PR A (#764) \| \| `format-check` (prettier) \| PR A (#764) \| \| `ruff-check` \| PR B (#765) |
| `@intentsolutionsio/zero-tech-debt@1.0.2` | 2026-05-17 | High | Released by `publish-changed-packages.yml` on push to `main`.  **npm:** https://www.npmjs.com/package/@intentsolutionsio/zero-tech-debt/v/1.0.2 **Source:** `plugins/skill-enhancers/zero-tech-debt` **Install:** `pnpm add @intentsolutionsio/zero-tech-debt@1.0.2` (or `/plugin install` via Claude Code marketplace)  ## What's Changed * feat(schema): 3-tier progressive disclosure (3.4.0) — L0 metadata index by @jeremylongshore in https://github.com/jeremylongshore/claude-code-plugins-plus-skills/pull/ |
| `@intentsolutionsio/cli-ux-tester@3.1.0` | 2026-05-12 | High | Released by `publish-changed-packages.yml` on push to `main`.  **npm:** https://www.npmjs.com/package/@intentsolutionsio/cli-ux-tester/v/3.1.0 **Source:** `plugins/testing/cli-ux-tester` **Install:** `pnpm add @intentsolutionsio/cli-ux-tester@3.1.0` (or `/plugin install` via Claude Code marketplace)  ## What's Changed * fix(validator): align agent field validation with current Anthropic sub-agents spec by @jeremylongshore in https://github.com/jeremylongshore/claude-code-plugins-plus-skills/pull |
| `v4.31.0` | 2026-05-08 | High | ## [4.31.0] - 2026-05-08  Four-day sprint after v4.30.0 — single-session execution of the "Use the Printing Press to Learn" plan, which mapped Matt Van Horn's CLI Printing Press against the IS stack and shipped the four real gaps it surfaced: generation capability (`/skill-creator --forge`), NOI cultural gate, JRig behavioral evaluation integration end-to-end, and marketplace trust signals (JRig-Verified badge + forge-generated provenance pill). The forge workflow is no longer theoretical — `plu |
| `v4.29.0` | 2026-05-03 | High | ## v4.29.0 — Validator + Testing + Release Automation  This release bundles 37 commits since v4.28.0. The CHANGELOG entry was originally drafted on 2026-04-28 for the validator work but was never tagged; this release expands it to cover everything that landed through 2026-05-02.  ### Highlights  - **Validator schema 3.3.1** + spec-compliance fixes (`compatible-with` → `compatibility` migration per AgentSkills.io) - **Fleet metadata migration** — ~3,200 SKILL.md files migrated across 8 PRs - **Te |
| `v4.28.0` | 2026-04-23 | High | **17 commits** since v4.27.0 · 4 feat · 12 fix · 1 chore · no breaking changes  ## Highlights  ### Gemini PR Review revival (#602) Fixed a 4-month silent-fail regression. The workflow was running green on every PR but posting **zero** review comments due to a broken MCP bridge pattern. Full fix bundle: - Trigger: `pull_request` → `pull_request_target` — fork PRs now get CI + Gemini feedback (previously received nothing) - Checkout: PR HEAD SHA pinned with `persist-credentials: false` - Prompt: I |
| `v4.27.0` | 2026-04-22 | High | ## LangChain Python Skill Pack v1.0  Complete 33-skill pack for production LangChain/LangGraph Python development.  ### Highlights  🔧 **Core Skills (8)**: model-inference, embeddings-search, sdk-patterns, reference-architecture, multi-env-setup, debug-bundle, deep-agents, langgraph-basics  🚀 **LangGraph Advanced (10)**: agents, checkpointing, human-in-loop, streaming, subgraphs, middleware-patterns, content-blocks, otel-observability  🏭 **Production Patterns (8)**: performance-tuning, cost-tu |
| `v4.26.0` | 2026-04-21 | High | ## Highlights  - **npm Download Tracking Infrastructure** - Daily stats aggregation, hero marquee showing top 8 packages with 30-day counts, Slack digest at 1pm Central via #operation-hired webhook - **npm Publish Workflows** - Mass publish (`publish-all-packages.yml`) and incremental publish (`publish-changed-packages.yml`) for @intentsolutionsio/* packages - **Plugin Package.json Scaffolding** - Generated package.json for 305+ catalog plugins under @intentsolutionsio scope - **README Awesome-L |
| `v4.25.0` | 2026-04-14 | Medium | ## Highlights  ### Shopify Skill Pack v2.0 Complete overhaul of the Shopify skill pack: - **30 → 38 skills** with 8 new skills for metafields, Functions (WASM), Storefront/headless, checkout extensions, theme performance, GraphQL cost optimization, B2B/wholesale, and AI Toolkit MCP wrapper - **116 reference files** extracted from all skills, keeping SKILL.md files concise - **Enterprise score: 81.9 → 93.1/100** with fixed descriptions, removed stubs, and added examples  ### Deep Evaluation Engin |

## Dependency audit

- **Score**: 100/100
- **Total deps**: 14
- **Resolved**: 14
- **Unresolved**: 0
- **License conflicts**: 0
- **Warnings**: 0
- **Scanned**: 2026-06-01

## Citation

- HTML: https://www.freshcrate.ai/projects/claude-code-plugins-plus-skills
- Markdown: https://www.freshcrate.ai/projects/claude-code-plugins-plus-skills.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/claude-code-plugins-plus-skills/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._