Skip to content
Back to search

claude-toolbox

SkillWorks with Claude CodeGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 15 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/serpro69/claude-toolbox with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/serpro69/claude-toolbox'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/serpro69--claude-toolbox/badge.svg)](/listings/serpro69--claude-toolbox)

HTML

<a href="/listings/serpro69--claude-toolbox"><img src="/api/listings/serpro69--claude-toolbox/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 32 lines
  1. {
  2. "name": "claude-toolbox",
  3. "owner": {
  4. "name": "serpro69",
  5. "url": "github.com/serpro69"
  6. },
  7. "metadata": {
  8. "description": "Development workflows from claude-toolbox"
  9. },
  10. "plugins": [
  11. {
  12. "source": "./klaude-plugin",
  13. "name": "kk",
  14. "version": "0.25.4",
  15. "author": {
  16. "name": "serpro69",
  17. "url": "github.com/serpro69"
  18. },
  19. "homepage": "https://serpro69.github.io/claude-toolbox/",
  20. "repository": "https://github.com/serpro69/claude-toolbox",
  21. "license": "Apache-2.0",
  22. "description": "Development workflow skills, commands, and hooks",
  23. "keywords": [
  24. "development",
  25. "workflow",
  26. "code-review",
  27. "testing",
  28. "documentation"
  29. ]
  30. }
  31. ]
  32. }
README.md · README · 123 lines
  1. <div align="center">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="docs/assets/images/lockup-dark.svg">
  4. <img src="docs/assets/images/lockup-light.svg" alt="claude-toolbox" width="720">
  5. </picture>
  6. </div>
  7. # claude-toolbox
  8. [![GitHub Release](https://img.shields.io/github/v/release/serpro69/claude-toolbox?style=for-the-badge&color=D9683D)](https://github.com/serpro69/claude-toolbox/releases)
  9. [![Mentioned in Awesome Claude Code](https://img.shields.io/badge/Awesome-Claude%20Code-fc60a8?style=for-the-badge&logo=awesomelists&logoColor=white)](https://github.com/hesreallyhim/awesome-claude-code)
  10. [![Documentation](https://img.shields.io/badge/docs-serpro69.github.io%2Fclaude--toolbox-blue?style=for-the-badge)](https://serpro69.github.io/claude-toolbox/)
  11. <div align="center"
  12. <picture>
  13. <img width="1080" alt="Terminal view" src="https://github.com/user-attachments/assets/27ef7269-0153-47c0-b07d-ed6a9504a176" />
  14. </picture>
  15. </div>
  16. `claude-toolbox` is a collection of "tools" for all your agentic workflows — pre-configured MCP servers, skills, sub-agents, commands, hooks, statuslines with themes, and more - everything you need for AI-powered development workflows, used and battle-tested daily on many of my own projects.
  17. **Supported providers:** [Claude Code](https://serpro69.github.io/claude-toolbox/latest/providers/claude-code/) · [Codex](https://serpro69.github.io/claude-toolbox/latest/providers/codex/)
  18. <div align="center">
  19. ## [Read the full documentation →](https://serpro69.github.io/claude-toolbox/latest/)
  20. <a href="https://serpro69.github.io/claude-toolbox/latest/">
  21. <img width="1080" alt="Docs landing page" src="https://github.com/user-attachments/assets/f6af0017-7f78-476b-8399-81eda8673d0a" />
  22. </a>
  23. ### [Or explore how claude-toolbox was used in a real project →](https://serpro69.github.io/claude-toolbox/latest/explore/)
  24. <a href="https://serpro69.github.io/claude-toolbox/latest/explore/">
  25. <img width="1080" alt="Explore page" src="https://github.com/user-attachments/assets/1adbbaa6-579c-4f27-94b1-8515cfefc2ec" />
  26. </a>
  27. </div>
  28. ---
  29. > [!IMPORTANT]
  30. > This project was created with the help of Claude-Code. Is it, however, always reviewed, tested, and reworked with a human-in-the-loop.
  31. >
  32. > No AI slop here. Purely AI-made skills are hot garbage, and that's putting it mildly.
  33. >
  34. > That said, if you have any problems with code that is written by AI - you've been warned. But, then again, why would you be interested in AI-related configs and skills in the first place... `¯\_(ツ)_/¯`
  35. ## Why claude-toolbox?
  36. Tools like Claude Code and Codex are powerful on their own, but LLMs don't know your development workflow. This project started as a way for me to streamline claude configurations across all my projects without needing to copy-paste things. With time, patterns and re-curring prompts evolved into skills and agents. Currently, claude-toolbox gives you two things:
  37. **A minimal, opinionated Claude Code and Codex configuration** — sensible permission baselines, a rich statusline, MCP server wiring, and sync infrastructure to keep it all up to date across your projects. Think of it as a dotfiles repo for Claude Code and Codex.
  38. **A structured development pipeline** — 16 workflow and utility skills with explicit multi-language support that take you from idea through design, implementation, code review, testing, to documentation, with persistent knowledge that carries across sessions.
  39. ```
  40. /kk:design → /kk:review-design → /kk:implement → /kk:review-code → /kk:test → /kk:document
  41. ```
  42. Out of the box you get:
  43. - **16 workflow and utility skills** — a complete development pipeline invoked as `/kk:<skill-name>`, plus utilities such as `/kk:clarify-docs` for improving existing documentation, PR drafts and issue descriptions, and explicit `/kk:handoff` publication of task context to a secret GitHub gist.
  44. - **Multi-language support** — precise and distinct instructions from design, to implementation, to testing, to review for: go, java, js/ts, kotlin, kubernetes, and python
  45. - **Multi-model code review** — independent reviewers using sub-agents and external models (Gemini, etc.)
  46. - **Persistent knowledge base** — findings, decisions, and conventions that survive across sessions via Capy
  47. - **Up-to-date library docs** — always-current documentation lookup via Context7
  48. - **Battle-tested configuration** — permissions, statusline themes, hooks, sensible defaults
  49. ## Choose Your Path
  50. **Starting a new project?** Use the template — you get the full configuration and plugin pre-wired, plus sync infrastructure to pull future updates.
  51. → [Template Setup](https://serpro69.github.io/claude-toolbox/latest/getting-started/template-setup/)
  52. **Existing project, want the full setup?** Adopt the configuration, plugin, and sync infrastructure without creating from the template.
  53. → [Adopting into Existing Repositories](https://serpro69.github.io/claude-toolbox/latest/getting-started/adopting/)
  54. **Just want the skills?** Install the kk plugin — no template needed.
  55. → [Plugin-Only Setup](https://serpro69.github.io/claude-toolbox/latest/getting-started/plugin-only/)
  56. ## Try It
  57. After setup, try the core workflow:
  58. For an optional conversation first, use `/kk:brainstorm` to think through a technical idea. It adapts the interview to your next decision and ends with a chat recap of decisions, rationale, and open assumptions. It creates no files or automatic handoff; request `/kk:design` when you want written planning.
  59. 1. **Write a plan.** Type `/kk:design` and describe a feature you want to build. Claude will ask refinement questions and confirm decisions, then produce design docs, an implementation plan, and a task list in `docs/feat/wip/`.
  60. 2. **Review the design.** Run `/kk:review-design your-feature` to catch gaps before writing code.
  61. 3. **Build it.** Type `/kk:implement` — Claude establishes the task's behavior and compatibility constraints, implements it, and supplies current evidence to independent review. Standalone fixes also work without design documents.
  62. 4. **Review the code.** `/kk:review-code` traces intended behavior, unchanged callers and affected compatibility contracts alongside SOLID, security and quality checks. Use `/kk:review-code:isolated` for independent review without the implementation conversation: an internal reviewer plus external review through PAL, using an API model when one is configured and otherwise your installed CLIs from other vendors (see [isolated reviews](docs/user-guide/skills.md#isolated-reviews-and-external-models)).
  63. Reviews distinguish current regressions from inherited issues and code support
  64. from deployment readiness. Missing evidence stays explicit; green tests support
  65. the paths exercised. Verification is proportionate to the change, while explicit
  66. repository and release checks remain required. See
  67. [functional review and implementation](docs/user-guide/skills.md#functional-review-and-implementation)
  68. for examples and limits.
  69. This is the core loop. See the [Skills documentation](https://serpro69.github.io/claude-toolbox/latest/user-guide/skills/) for all available skills and the full workflow pipeline.
  70. To clarify a bug report or feature request, use `/kk:clarify-docs issue-draft.md`
  71. or supply an issue URL or pasted description with a local destination. The skill
  72. preserves evidence limits and produces a local draft; it does not publish or
  73. implement the issue. See [issue-description examples](docs/user-guide/skills.md#clarify-an-issue-description)
  74. for output selection and audience rules. Clarification remains optional.
  75. ## Examples
  76. Examples of actual Claude Code workflows executed using this template's configs, skills, and tools: [examples/](./examples)
  77. ## Contributing
  78. Contributions are welcome! See the [Contributing guide](https://serpro69.github.io/claude-toolbox/latest/contributing/) for guidelines, [Architecture](https://serpro69.github.io/claude-toolbox/latest/contributing/architecture/) for how components fit together, and [Testing](https://serpro69.github.io/claude-toolbox/latest/contributing/testing/) for test conventions.
  79. ## License
  80. Copyright &copy; 2025 - present, [serpro69](https://github.com/serpro69)
  81. Distributed under the Apache License 2.0.
  82. See [`LICENSE.md`](https://github.com/serpro69/claude-toolbox/blob/master/LICENSE.md) file for more information.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.