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/borghei/Claude-SkillsWrote 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/borghei/claude-skills/engineering)<a href="https://agentmods.dev/plugins/borghei/claude-skills/engineering"><img src="https://agentmods.dev/badge/plugins/borghei/claude-skills/engineering/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/borghei/claude-skills/engineering"><img src="https://agentmods.dev/badge/plugins/borghei/claude-skills/engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
engineering-advanced-skills 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 13d 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 74 skills travel with it, and installing the plugin installs all of them — 3,744 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cloud-security A 49 tokens
- Skill security-audit A 44 tokens
- Skill agent-harness A 50 tokens
- Skill code-tour A 40 tokens
- Skill agent-workflow-designer A 50 tokens
- Skill agentic-evaluation-framework A 51 tokens
- Skill claude-code-mastery A 109 tokens
- Skill context-engine A 41 tokens
- Skill data-quality-auditor A 52 tokens
- Skill doc-drift-detector A 53 tokens
- Skill feature-flags-architect A 48 tokens
- Skill mcp-server-builder A 49 tokens
- Skill ms365-tenant-manager A 46 tokens
- Skill playwright-pro A 52 tokens
- Skill self-improving-agent A 50 tokens
- Skill agent-designer A 42 tokens
- Skill agent-protocol A 45 tokens
- Skill agenthub A 44 tokens
- Skill api-design-reviewer A 49 tokens
- Skill api-test-suite-builder A 50 tokens
- Skill aws-solution-architect A 51 tokens
- Skill azure-cloud-architect A 42 tokens
- Skill batch-api-orchestrator A 53 tokens
- Skill changelog-generator A 48 tokens
- Skill chaos-engineering A 47 tokens
- Skill ci-cd-pipeline-builder A 52 tokens
- Skill code-reviewer A 57 tokens
- Skill codebase-onboarding A 50 tokens
- Skill codex-cli-specialist A 50 tokens
- Skill computer-use-automation A 56 tokens
- Skill database-designer A 46 tokens
- Skill database-schema-designer A 49 tokens
- Skill dependency-auditor A 45 tokens
- Skill docker-development A 43 tokens
- Skill env-secrets-manager A 53 tokens
- Skill extended-thinking-architect A 51 tokens
- Skill focused-fix A 56 tokens
- Skill gcp-cloud-architect A 53 tokens
- Skill google-workspace-cli A 47 tokens
- Skill helm-chart-builder A 44 tokens
- Skill incident-commander A 44 tokens
- Skill interview-system-designer A 44 tokens
- Skill kubernetes-operator A 44 tokens
- Skill migration-architect A 38 tokens
- Skill monorepo-navigator A 58 tokens
- Skill observability-designer A 52 tokens
- Skill performance-profiler A 51 tokens
- Skill pr-review-expert A 49 tokens
- Skill prompt-engineer-toolkit A 52 tokens
- Skill rag-architect A 49 tokens
- Skill release-manager A 40 tokens
- Skill release-orchestrator A 49 tokens
- Skill runbook-generator A 50 tokens
- Skill saas-scaffolder A 60 tokens
- Skill senior-backend A 47 tokens
- Skill senior-cloud-architect A 99 tokens
- Skill senior-computer-vision A 47 tokens
- Skill senior-data-engineer A 51 tokens
- Skill senior-data-scientist A 102 tokens
- Skill senior-frontend A 48 tokens
- Skill senior-fullstack A 48 tokens
- Skill a11y-audit A 49 tokens
- Skill ai-security A 50 tokens
- Skill design-auditor A 49 tokens
- Skill devops-workflow-engineer A 48 tokens
- Skill llm-cost-optimizer A 48 tokens
- Skill senior-devops A 48 tokens
- Skill browser-automation A 48 tokens
- Skill prompt-governance A 47 tokens
- Skill red-team A 47 tokens
- Skill secrets-vault-manager A 47 tokens
- Skill qa-browser-automation B 43 tokens
- Skill senior-architect B 44 tokens
- Skill git-worktree-manager C 47 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.
- 13d ago Changed 556496f64e7f
- 1mo ago First seen · 14 lines scan A 6797cc268b09
engineering-advanced-skills is a plugin published in the GitHub repository borghei/Claude-Skills (949 stars, last pushed 13d 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 2026-09-03.
Other plugins, from other repositories
fiveai-skills
Curated FiveM development skills for coding agents.
polish-marketing-skills
Copywriting marketingowy, sekwencje mailowe, social media i marketing psychology — skille marketera operującego w Polsce.
dspy-build-skills
Skills for building AI features: routing, classification, search, database Q&A, summarization, parsing, tool use, content generation, translation, recommendations, redaction, record matching, data cleaning, anomaly detection, notifications, image understanding, text rewriting, chatbots, agents, scoring, moderation…
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.