AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
Claude Code Templates
Claude Code Templates logo

Claude Code Templates

Active·★ 33.9k·MIT·Updated 2026-11-17
★ Most Popular

Claude Code Templates is a catalog and CLI for installing agents, commands, skills, MCP configuration and other Claude Code components. We ran the source CLI at commit 177c92592977ae1f94a9d20585cd25de26e1314b, whose package declares 1.32.1, on macOS 26.6.2 with Node.js 26.3.0 ARM64. Dependencies came from the source lockfile. This identifies a source build, not a separately verified npm release tarball. Tracking was disabled and all writes targeted artificial projects.

A real network installation selected one agent, one command, a PostgreSQL MCP configuration and a frontend skill. Four downloaded files matched the pinned source hashes; the existing artificial MCP entry remained alongside the new one. Reinstalling the agent replaced a handwritten local edit. In a fresh directory, the component command with --dry-run still created its agent file. A nonexistent skill printed failure but returned process status zero. Thirty-one supplementary upstream tests passed, with simulated network cases clearly separated from the live installation.

The practical benefit is assembling a reviewed selection of configuration, rather than proving those instructions effective. Selected ordinary component URLs use main, so pinning the CLI alone does not pin future downloads. An initial default Node fetch failed; the recorded retry succeeded with --use-env-proxy and normal TLS validation. We did not run Claude tasks, installed hooks, databases, plugins or dashboards. The selected MCP entry still contained a placeholder connection string; installation success is not service connectivity.

Read the full review, verification scope and sources →

Hands-on tested · Tested on 2026-11-07 with source CLI 1.32.1 at 177c92592977ae1f94a9d20585cd25de26e1314b; not the npm release tarball.

Setup: macOS 26.6.2; Node.js 26.3.0 ARM64; CPython 3.12.13 x86_64 for Anthropic scripts; disposable project files only.

Commands run

node doc/review-fixtures/skills-knowledge-20261107/verify-templates.mjs <sources>/claude-code-templates <fresh-work> /tmp/templates-results.json

What we saw

  • Four component types installed over the real network; four downloaded files matched pinned source hashes, and an existing artificial MCP entry survived merging.
  • Agent reinstallation replaced a local edit. Component --dry-run wrote an agent file. A missing skill printed failure but exited zero.
  • Thirty-one upstream helper tests passed, with fake network cases recorded separately. Initial fetch failed; supported environment-proxy retry worked. No Claude task, installed hook, plugin enablement or database connection.

Data as of 2026-11-15.

License
MIT
Latest release
v1.29.7 · 2026-10-09
Last commit
2026-11-15
Contributors
176
Forks
3,984
Open issues and PRs
517
First published
2025-07-04

Source: GitHub, npm and PyPI public APIs.

#agent-skills#ai-agents#anthropic#anthropic-claude#claude#claude-code#claude-code-plugins#cli
$ Install
$ npx claude-code-templates@latest
↗ Visit site★ GitHub
01

Features

01Installs individual components or combines several in one CLI command.
02Catalog previews the files that components write.
03Provides settings, hooks, mods, loops, sandboxes and project templates.
04Offers local analytics and conversation browsing dashboards bound to loopback addresses.
05Includes health checks for Claude Code installations and project configuration.
02

Why choose it

+The selected agent, command and skill files matched the pinned source after real downloads.
+The tested MCP merge preserved an existing entry while adding PostgreSQL configuration.
+One CLI assembled four component types into the expected project paths.
03

Trade-offs

!The tested component --dry-run still wrote a file, and agent reinstallation replaced a local edit.
!A missing skill printed failure but exited zero, complicating shell automation.
!Selected downloads follow main; installed behavior and connected services need separate validation.
05

Maintenance check

ActiveChecked: 2026-11-07
Last commit
2026-11-07
Commits, last 90 days
100+
Releases, last 90 days
3
Latest release
v1.29.7 (2026-10-09)
Open issues
468
Recent issues with at least one comment
—
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 35, 28, 27, 24, 46, 63, 58, 62, 27, 54, 38, 80

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

04

Who it fits

Pick it if
  • You want a small reviewed selection of Claude Code components.
  • You can install into a disposable target, compare files and retain source identities.
Look elsewhere if
  • You need a zero-write component preview from the tested dry-run path.
  • You expect installation to prove model quality or configure a working database automatically.
06

Compatibility

Claude Code
Configuration components for Claude Code
Verified via docs
Node.js
Distributed through npm and npx
Verified via docs
07

Quick start

1
$ npx claude-code-templates@latest
08

Use cases

↳Configure a project with reusable Claude Code components.
↳Install a specific skill, agent or MCP integration.
↳Inspect local Claude Code sessions and diagnose setup problems.
09

Alternatives

⚡Top VS:
VSmirrord★5.4k→VSpstack-claude★4.4k→VStaste-skill★117.7k→VSself-host★1.6k→
mirrord logo
mirrord★ 5.4k
Run any process, on your machine or in an AI agent's environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic.
VSCompare→
pstack-claude logo
pstack-claude★ 4.4k
Claude Code, Codex, Copilot, Pi, OpenCode, Muse, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.
VSCompare→
taste-skill logo
taste-skill★ 117.7k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
VSCompare→
self-host logo
self-host★ 1.6k
Replace the SaaS you pay for. One binary installs and runs self-hosted apps at home, no Docker knowledge needed. Terminal dashboard for you, plain commands for your agent.
VSCompare→
WebPerf Snippets logo
WebPerf Snippets★ 1.5k
Tested JavaScript snippets that measure and debug web performance. Your AI agent runs them for you, or you run them yourself in DevTools: the same code every time.
VSCompare→
Chisle logo
Chisle★ 1.2k
Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.
VSCompare→
claude-skills logo
claude-skills★ 12.4k
67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.
coder_eval logo
coder_eval★ 160
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06Compatibility07Quick start08Use cases09Alternatives
davila7 /
claude-code-templates
↗

Installs reusable Claude Code configuration; inspect writes and failure status

33.9k4.0kMIT
Last commit1d ago
StatusActive
CategoryDev Tooling
Contributors176
Latest releasev1.29.7
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.