The best Claude Code plugins and agent skills in 2026
The best Claude Code plugins and agent skills right now are Superpowers, Matt Pocock's Skills and Anthropic Skills, out of 25 we have reviewed. Each is ranked by our rating, with its price, our verdict and who it suits.
Updated Oct 24, 2026 · Ranked from our reviews · How we review
- 1
A discipline layer that makes a coding agent behave like a careful junior engineer, and worth its extra tokens on anything bigger than a one-line fix.
Best for: Developers who want an agent to run multi-hour features with a plan, tests and review built in.
Price: Free and open source (MIT). You pay for the model usage of the agent you run it in.
Read our Superpowers review4.7/5 - 2
Matt Pocock's skills make the agent argue the plan out with you before it writes code, and /grill-me alone justifies the install.
Best for: Engineers who want lightweight planning and TDD habits without handing the process to a framework.
Price: Free and open source (MIT). You pay for your agent's model usage.
Read our Matt Pocock's Skills review4.5/5 - 3
Read it before writing a skill of your own, and install it if Claude Code has to handle Office files and PDFs; just don't mistake the document skills for something you can fork.
Best for: Anyone writing skills, and Claude Code users who need Office and PDF handling.
Price: Free. Example skills are Apache-2.0; the document skills are source-available, not open source.
Read our Anthropic Skills review4.4/5 - 4
ccusage is the meter every heavy agent user should run, provided they read its dollar column as what the work would have cost on the API, not what they paid.
Best for: Anyone who wants to track or compare token use across agent sessions.
Price: Free and open source (MIT).
Read our ccusage review4.4/5 - 5
A generic "check for OWASP issues" prompt is a guess; this is how a working audit firm actually looks for bugs, written down for your agent.
Best for: Teams that want structured, credible security review from their coding agent before risky merges.
Price: Free under CC BY-SA 4.0.
Read our Trail of Bits Skills review4.4/5 - 6
Addy Osmani's pack turns senior-engineer habits into gates an agent cannot talk its way past, and it is the rare skill set that takes the browser seriously.
Best for: Web developers who want one structured skill pack from spec to launch.
Price: Free and open source (MIT). You pay for your agent's model usage.
Read our Agent Skills (Addy Osmani) review4.3/5 - 7
Start here before adding any third-party marketplace: commit-pinned entries and visible context cost make it the safest default, though a listing is not a security audit.
Best for: Every Claude Code user, as the first place to look for plugins.
Price: Free. The catalogue repo is Apache-2.0; each plugin has its own licence, and many vendor plugins need a paid account with that vendor.
Read our Claude Code official plugin marketplace review4.3/5 - 8
A real detector and a shared design vocabulary make this the design skill worth installing, provided you switch off telemetry and keep it the only design skill in the project.
Best for: Developers whose agents build frontend UI and want it to look less generic.
Price: Free and open source (Apache-2.0).
Read our Impeccable review4.3/5 - 9
Spec Kit turns agent work into reviewable documents in git, and charges for it in hours of human reading per feature.
Best for: Teams that want written, reviewable specs before an agent writes code.
Price: Free and open source (MIT).
Read our Spec Kit review4.3/5 - 10
For a Claude Code user this is a one-command security win, with a reviewer that is not grading its own homework.
Best for: Claude Code users who want security review on every change without setting anything up.
Price: Free plugin under Apache 2.0; the two model-backed reviews use your Claude or API usage.
Read our security-guidance plugin (Claude Code) review4.2/5 - 11
Worth installing on large repos where your agent keeps grepping, provided you treat the benchmark numbers as the vendor's own and choose the docs backend deliberately.
Best for: Teams with large codebases who want their agent to navigate structure instead of grepping.
Price: Open-source engine free (Apache-2.0, with an MIT licence file also in the repo). Graphify Cloud has a free hosted tier and per-seat Pro and Teams plans with prices not published; self-hosted Enterprise is in early access.
Read our Graphify review4.1/5 - 12
A skill that turns a concept into a machine readers will stop and play with, and charges for it in long, token-hungry sessions.
Best for: Technical writers and developers who want interactive explanatory figures for docs, posts and landing pages.
Price: Free and open source under MIT. Runs on the agent subscription or API you already use.
Read our Anatomy review4.0/5 - 13
The seatbelt for the damage a sandbox allows on purpose: force-pushes, hard resets and rm -rf inside your own project.
Best for: Anyone letting a coding agent run shell commands without approving each one.
Price: Free and open source under MIT.
Read our CC Safety Net review4.0/5 - 14
A capable local switchboard for running coding agents on cheaper models, as long as you accept that Anthropic will not support the result and the edits will be worse.
Best for: Developers who want to run Claude Code or other agents on cheaper or local models.
Price: Free and open source (MIT). You pay each model provider you route to.
Read our Claude Code Router review4.0/5 - 15
A sound way to put a second model's review on Claude's work, held back by a maintainer queue that has not moved since July.
Best for: Claude Code users with a ChatGPT or OpenAI account who want a second-model review.
Price: Free and open source (Apache-2.0). Usage counts against your ChatGPT plan or OpenAI API billing.
Read our Codex plugin for Claude Code review4.0/5 - 16
A free catalogue of specialist subagents that rewards picking two plugins and reading them, and punishes installing all 94.
Best for: Developers who want ready-made specialist subagents for their language or stack.
Price: Free and open source (MIT). You pay for your agent's model usage.
Read our wshobson/agents review4.0/5 - 17
The rare AI audit tool that assumes its own findings are wrong until another agent fails to knock them down.
Best for: Security teams auditing a codebase who want verified findings rather than a long list of maybes.
Price: Free under MIT; audits use a lot of model tokens.
Read our Cloudflare Security Audit Skill review3.9/5 - 18
A sensible always-on rule set you can read in two minutes; useful, but it is a starting file, not a tool.
Best for: Developers who want a short, ready-made CLAUDE.md that discourages over-building.
Price: Free. The README says MIT, but the repo has no LICENSE file and GitHub detects no licence.
Read our Karpathy-inspired CLAUDE.md review3.9/5 - 19
BMAD earns its paperwork on projects with stakeholders who sign things off, and charges for it in hours on everything smaller.
Best for: Teams on larger projects that want PRDs, architecture and stories generated and reviewed.
Price: Free and open source (MIT). "BMad" and "BMAD-METHOD" are trademarks of BMad Code, LLC.
Read our BMAD Method review3.8/5 - 20
claude-obsidian treats a notes vault like a database, with transactions and citations, which makes it trustworthy and slow to adopt.
Best for: Obsidian users who want Claude Code to build and query a cited research wiki.
Price: Free and open source (MIT). You pay for your agent's model usage.
Read our claude-obsidian review3.8/5 - 21
ECC is a parts bin rather than a workflow: useful in a minimal profile, a standing tax on context at full size.
Best for: Claude Code power users who want a large toolkit and will trim it to a minimal profile.
Price: Free and open source (MIT). ECC Pro GitHub App for private repos is $19 per seat a month; Enterprise is quoted. You pay for your agent's model usage.
Read our Everything Claude Code (ECC) review3.8/5 - 22
NotebookLM's full feature set in an agent's hands, held together by undocumented Google endpoints and a login you should not give it lightly.
Best for: Researchers who want Claude Code to build and query NotebookLM notebooks.
Price: Free and open source (MIT). NotebookLM limits depend on your Google account tier.
Read our notebooklm-py review3.8/5 - 23
Real cross-session memory for Claude Code, wrapped in an installer that steers you towards a hosted subscription and a compression bill you have to watch.
Best for: Developers on long-running projects who want the agent to remember past sessions.
Price: Open source (Apache-2.0). Compression runs on your Anthropic plan or your own key. Hosted CMEM plans: Pro $30/month, Heavy $70/month, Max $100/month with overages; TeamBrain pricing not announced.
Read our claude-mem review3.7/5 - 24
Worth trying for long sessions that lose the thread after compaction; nobody has yet shown the free plugin lowers your bill.
Best for: Claude Code users whose long sessions lose track of their work after compaction.
Price: Plugin free (Elastic License 2.0). Hosted gateway: 1,000 free requests once; Starter $20/month (10,000 requests); Pro $49/month (50,000 requests); you pay your model provider directly.
Read our context-mode review3.6/5 - 25
It makes shell output shorter, which is not the same as making Claude Code cheaper, and both independent cost tests found it was not.
Best for: Developers with very noisy shell output who will measure the effect themselves.
Price: Free (Apache-2.0 CLI plus BUSL-1.1 engine; Apache-only rtk-oss available). Commercial resale needs a licence. RTK Pro team edition is paid, with a 7-day trial.
Read our rtk (Rust Token Killer) review3.4/5