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.
/plugin marketplace add rios0rios0/guidenpx agentmods add plugins/rios0rios0/guide/engineering-standardsgit clone --depth 1 https://github.com/rios0rios0/guideWrote 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/rios0rios0/guide/engineering-standards)<a href="https://agentmods.dev/plugins/rios0rios0/guide/engineering-standards"><img src="https://agentmods.dev/badge/plugins/rios0rios0/guide/engineering-standards.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
engineering-standards 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 yesterday.
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.
What it actually says
{
"name": "engineering-standards",
"source": "./.github/workflows/generate-ai-rules",
"description": "Engineering standards with 7 agents, 8 commands, 5 skills, and 1 hook for software development best practices"
}What it installs
The manifest is a name and a version. 5 skills, 8 commands, 7 agents travel with it, and installing the plugin installs all of them — 605 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill fix-guardrails A 50 tokens
- Skill scaffold-go-project A 39 tokens
- Skill scaffold-frontend-project A 48 tokens
- Skill scaffold-python-package A 55 tokens
- Skill check-standards A 24 tokens
- Command fix-guardrails A 0 tokens
- Command fix-ci A 0 tokens
- Command resolve-pr-comments A 0 tokens
- Command scaffold-go-project A 0 tokens
- Command scaffold-frontend-project A 0 tokens
- Command scaffold-python-package A 0 tokens
- Command check-standards A 0 tokens
- Command sync-repos A 0 tokens
- Agent chezmoi A 54 tokens
- Agent pr-review-resolver A 55 tokens
- Agent changelog-enforcer A 77 tokens
- Agent git-workflow A 42 tokens
- Agent security-auditor A 48 tokens
- Agent code-reviewer A 43 tokens
- Agent bulk-operations C 70 tokens
What ships with it
1 file beside marketplace.json#engineering-standards in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 5 lines scan A 70e161c06755
engineering-standards is a plugin published in the GitHub repository rios0rios0/guide (2 stars, last pushed 2d ago), licensed MIT. 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
google-workspace-mcp
Complete Google Workspace integration -- Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, and Custom Search via MCP with workflow guidance.
caveman
Ultra-compressed communication mode. Cuts 65% of output tokens against an unprompted baseline (measured) while keeping full technical accuracy by speaking like a caveman.
claude-flow
Enterprise AI agent orchestration plugin with 150+ commands, 74+ specialized agents, SPARC methodology, swarm coordination, GitHub integration, and neural training capabilities.
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.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.