Best Claude Code Plugins 2026: 62 Agentic Workflow Tools

Claude Code is most powerful when it stops being an autocomplete and becomes a fleet of agents that verify their own work, review each other, pull their own context, and run on a schedule. Plugins are how you package that practice so it is reusable across every repository you touch.

This guide walks through all 62 plugins in the open-source matthews-agentic-plugins marketplace, grouped so you can find the right one fast. Every plugin ships an auto-invocable skill, has zero runtime dependencies, and is MIT-licensed. The full source is public on GitHub — clone it, read it, and adapt it to your own stack.

Which are the best Claude Code plugins to install first?

If you want a short answer, install these five first — they cover self-verification, review, security, and durable context, which is where most teams feel the bottleneck first.

• memory — durable, auto-surfaced context so Claude stops forgetting between sessions.
• verify-before-review — runs tests, lint, and build so Claude checks its own work first.
• code-review-agent — a subagent that reviews your working diff for bugs before you do.
• security-review-agent — flags common vulnerabilities in your changes, ranked by severity.
• skills-connector — scaffold and wire up your own reusable, auto-invoked skills library.

Why these Claude Code plugins are worth installing

Every plugin here removes a specific kind of friction you have probably already felt. Instead of babysitting the agent line by line, you let it verify, review, and remember — then you review the result, not every keystroke. That is the whole shift from using Claude Code as autocomplete to running it as a small, accountable team.

• Stop being the bottleneck: Claude runs tests, lint, and build and reviews its own diff before the work ever reaches you.
• Catch problems early: leaked secrets, common vulnerabilities, and breaking API changes get flagged in the diff, not in production.
• Keep what you learn: durable memory means you never explain the same fix twice — Claude carries the lesson into the next session.
• One command, zero lock-in: everything is open source, dependency-free, and MIT-licensed — install what helps, delete what does not.

How to install the marketplace

Adding the marketplace makes every plugin available; a plugin only does something once you install it into your session. Add the marketplace once, then install any plugin by name. Browse everything with the marketplace list command, and after installing run reload-plugins so Claude Code picks the new components up.

1. Add the marketplace once: run /plugin marketplace add matthews-wong/claude-code-plugins.
2. Install any plugin by name, for example /plugin install memory@matthews-agentic-plugins.
3. Browse everything with /plugin marketplace list, then run /reload-plugins so Claude Code loads the new components.

# 1) Add the marketplace (one time)
/plugin marketplace add matthews-wong/claude-code-plugins

# 2) Install any plugin by name
/plugin install memory@matthews-agentic-plugins
/plugin install verify-before-review@matthews-agentic-plugins

# 3) Browse everything, then reload
/plugin marketplace list
/reload-plugins

The four ways a plugin runs

A Claude Code plugin is a manifest plus the components it ships. There are four component types, and knowing which one a plugin uses tells you how it fires.

Organized by the five stages of AI adoption

The categories map to the maturity model from Boris Cherny's Steps to AI adoption with Claude Code. The idea: teams advance not by buying more tokens but by finding the next bottleneck and layering the right guardrail. Each group below is the concrete guardrail for one step-up.

What a day with these plugins actually looks like

The plugins are useful on their own, but the point is how they chain together on a normal feature. Here is the loop most teams settle into once a handful of these are installed.

1. You describe the feature. context-puller gathers the README, ADRs, and git history into a grounded brief, so Claude starts with the right context instead of guessing.
2. Claude writes the change. test-guardian runs the fast tests after each edit, and secret-scanner watches the diff so an API key never slips into a commit.
3. Before you look, verify-before-review runs tests, lint, and build; then code-review-agent and security-review-agent review the diff and rank what they find by severity.
4. You review the summary, not every line. Whatever you correct, memory records — so next session Claude already knows the rule and does not repeat the mistake.
5. You ship. conventional-commits formats the commit message and release-manager handles the semver bump, tag, and release notes. That is the full loop, and it runs on plugins you installed in minutes.

All 62 plugins, by category

Verification & review — Claude verifies its own work first

The first bottleneck in agentic coding is your attention. These plugins give Claude Code an end-to-end self-verification loop so tests, lint, build, and review all run before a human ever looks at the diff.

Permissions & guardrails — cut review friction safely

Approving every tool call by hand is friction. These plugins pre-approve a vetted set of safe commands and analyze what you keep denying, so Claude stops asking about the harmless things.

Context & skills — ground agents and build a reusable library

Trust and context are the bottleneck from parallel to supervised work. These plugins pull the right context before a task and turn your standards into reusable skills.

Orchestration & loops — scale beyond one agent

Throughput is the next ceiling. These plugins kick off agents in parallel, isolate them on git worktrees, and turn repeatable work into loops and scheduled routines.

Cost & governance — control spend and keep oversight

At team scale, cost and oversight become the constraint. These plugins set a model-selection policy, track token usage, and export telemetry with spend caps.

Language & stack skills — auto-invoke as you code

These skills fire automatically when you write or review matching code — no command needed. Each applies modern, opinionated defaults for its language or layer.

Security & compliance — enterprise guardrails

The enterprise layer starts with keeping secrets, vulnerable dependencies, and mishandled data out of your repository — mapped to controls auditors recognize.

Governance & standards — make good practice the default

Consistent history, decisions, and ownership are what let a team move fast without breaking process. These plugins enforce PR standards, commits, ADRs, releases, and ownership.

Quality & reliability — gates that catch regressions

Reliability comes from gates that fail loudly. These plugins guard coverage, API contracts, docs freshness, incident response, and infrastructure policy.

Context engineering — memory and auto-learning

Agents forget between sessions; a file does not. These plugins give Claude Code durable, folder-scoped memory with local vector search plus rules it promotes from recurring lessons. Start with the all-in-one memory plugin.

Security & policy skills — auto-invocable reviews

These skills pull themselves in when your task matches — threat modeling a feature, hardening a Dockerfile, checking a K8s manifest, reviewing a migration, or auditing accessibility.

Workflow patterns — straight from Claude Code best practices

Packaged directly from Anthropic's official Claude Code best-practices guide: verify the app for real, write a spec, review with fresh context, clean a stuck session, and fan out a large migration.

Modeled on Boris Cherny's workflow

Plugins that operationalize how Claude Code's creator actually works — his own subagents and engineering principles, distilled into components you can install.

Deep dive: the memory plugin

If you install only one plugin, make it memory. It is the all-in-one context engine: folder-scoped learnings retrieved by hybrid vector search, plus recurring lessons promoted into durable rules that surface at the start of every session. One SessionStart hook surfaces both, one store holds everything, and a status command shows you what Claude remembers.

Confirming a skill actually fired

Auto-invocation is model-driven routing, not a hardwired switch — a skill fires when your task matches its description. After installing or updating, run reload-plugins, then give a task that should match and confirm Claude loads the skill instead of improvising. If it does not fire, the description usually needs sharpening — that is the single most common cause.

Clone the repo and make it yours

The whole marketplace is open source. Clone it to read how each plugin is built, fork it to adapt the hook scripts to your stack, or install straight from the marketplace command above. The plugins are intentionally small and dependency-free so they are easy to tailor.

Start small: install verify-before-review and code-review-agent to get self-verification, add memory so lessons persist, then layer the enterprise and language plugins as your team's bottleneck moves. Behavior, not your license tier, determines how far up the adoption curve you actually are.

Related reading

• How Claude Code works: agentic coding explained
• Agentic coding workflow best practices
• Multi-agent orchestration with subagents
• Context engineering for LLM agents
• Claude Code vs Codex for agentic coding