Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/artubss/SKILLS-CLAUDE-CODEWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/artubss/skills-claude-code/dev-tools)<a href="https://agentmods.dev/plugins/artubss/skills-claude-code/dev-tools"><img src="https://agentmods.dev/badge/plugins/artubss/skills-claude-code/dev-tools/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/artubss/skills-claude-code/dev-tools"><img src="https://agentmods.dev/badge/plugins/artubss/skills-claude-code/dev-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dev-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 17 skills, 16 commands travel with it, and installing the plugin installs all of them — 2,019 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ux-audit A 217 tokens
- Skill deep-research A 108 tokens
- Skill fork-discipline A 124 tokens
- Skill onboarding-ux A 119 tokens
- Skill roadmap A 110 tokens
- Skill ux-extract A 121 tokens
- Skill vitest A 87 tokens
- Skill app-docs A 115 tokens
- Skill ux-compare A 114 tokens
- Skill brains-trust A 0 tokens
- Skill project-docs A 91 tokens
- Skill responsiveness-check A 85 tokens
- Skill codex-review A 129 tokens
- Skill git-workflow A 52 tokens
- Skill github-release A 65 tokens
- Skill project-health B 126 tokens
- Skill team-update B 94 tokens
- Command ux-audit A 101 tokens
- Command deep-research A 8 tokens
- Command app-docs A 11 tokens
- Command project-health A 11 tokens
- Command roadmap A 15 tokens
- Command fork-discipline A 12 tokens
- Command onboarding-ux A 17 tokens
- Command git-workflow A 13 tokens
- Command project-docs A 7 tokens
- Command agent-browser A 7 tokens
- Command brains-trust A 8 tokens
- Command responsiveness-check A 6 tokens
- Command ux-compare B 11 tokens
- Command team-update B 12 tokens
- Command ux-extract B 16 tokens
- Command release B 7 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 9 lines scan A b42103efb1f2
dev-tools is a plugin published in the GitHub repository artubss/SKILLS-CLAUDE-CODE (11 stars, last pushed 5mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
drawio
Draw.io MCP: built-in editor, page/layer tools, AWS/GCP/Azure/Cisco stencils.
terravision-cloud-diagrams
Draw professional cloud architecture diagrams (AWS, Azure, GCP) from a one-sentence description of your idea, a JSON graph or Terraform code using TerraVision.
terravision
Draw professional cloud architecture diagrams (AWS, Azure, GCP) with official provider icons from a one-sentence description of your idea, a JSON graph or Terraform code.
aws-architecture-diagram
Generate AWS architecture diagrams as draw.io XML with 270+ verified icons, left-to-right layout, and reference templates.
oracle-diagram-generator
Generate professional OCI architecture diagrams with Python diagrams library (official OCI icons) or Mermaid.js.
aws-diagrams
Discover AWS infrastructure and generate architecture diagrams using AI.