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 smk-labs/claude-pluginsnpx agentmods add plugins/smk-labs/claude-plugins/marketplacegit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/marketplace)<a href="https://agentmods.dev/plugins/smk-labs/claude-plugins/marketplace"><img src="https://agentmods.dev/badge/plugins/smk-labs/claude-plugins/marketplace.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
smk marketplace 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "smk",
"owner": {
"name": "Seyed M. Keramati",
"url": "https://github.com/SMKeramati"
},
"metadata": {
"description": "Everything I have built for Claude Code: skills, commands, agents, and packaged tools, in one place.",
"version": "1.1.0"
},
"plugins": [
{
"name": "cursor-delegate",
"source": "./cursor-delegate",
"description": "Run coding and writing tasks on your Cursor subscription's quota instead of Claude's. Claude plans and reviews, Cursor workers execute, one task at a time or as a parallel fleet. Long jobs run as short resumable legs, so a dropped connection costs one leg and never the work. Includes copy-writing-fa for Persian web copy, with fa-lint as the gate.",
"version": "1.9.1",
"category": "engineering"
},
{
"name": "spring-clean",
"source": "./spring-clean",
"description": "Deep-clean a repo against a declared scoreboard, then give it rules at both layers. Delete dead surfaces, move dev docs out of the code tree, split oversized files and draw package boundaries, with the plan written down so a long pass survives a dead context; then sort every rule by what it hands the model, tell the facts it cannot infer where a session starts, count anything a script could count, and cap the set inside the check file itself.",
"version": "3.0.0",
"category": "engineering"
},
{
"name": "portal-skills",
"source": "./portal-skills",
"description": "Platform engineering and security: GitLab CI/CD and Helm charts for Kubernetes, pod rightsizing from real Prometheus data, a secure-coding baseline that applies while you write, and a deep OWASP reference (Top 10:2025, LLM Top 10, Agentic AI).",
"version": "1.0.0",
"category": "engineering"
},
{
"name": "readable",
"source": "./readable",
"description": "Replies as styled cards instead of raw chat text. Persian and RTL always render correctly, EngliThe plugins it lists here
This marketplace lists 11 plugins kept in the same repository. Each has its own page, its own measurements and its own install command.
- Plugin readable 5 inside A not measured
- Plugin cursor-delegate 4 inside A not measured
- Plugin spring-clean 2 inside A not measured
- Plugin learnable 6 inside A not measured
- Plugin getpix 4 inside A not measured
- Plugin open-design-guide 1 inside A not measured
- Plugin portal-skills 4 inside A not measured
- Plugin fig 2 inside A not measured
- Plugin principles-first 1 inside A not measured
- Plugin daily-tools 9 inside C not measured
- Plugin decode 1 inside C not measured
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.
- today Changed 7f974d18e6c2
- 3d ago First seen · 109 lines scan A 7e8745555db9
smk marketplace is a plugin published in the GitHub repository smk-labs/claude-plugins (11 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 2026-08-30.
Other plugins, from other repositories
pm-ai-shipping
AI Shipping Kit — for PMs and founders accountable for AI-built code. Document a vibe-coded app, audit it for intended-vs-implemented security gaps and performance issues, and produce a reviewer-ready shipping packet.
pm-execution
Execution and product management skills: PRDs, OKRs, roadmaps, sprints, pre-mortems, stakeholder maps, user stories, prioritization frameworks, and more.
pm-go-to-market
Go-to-market skills for PMs: GTM strategy, growth loops, GTM motions, beachhead segments, and ideal customer profiles.
handbook-agent-spec-kit
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation.
handbook-dotnet
.NET development tools including automatic CSharpier formatting for C# files and dotnet run file support.
bash-specialist
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX via Charmbracelet gum. Skills: gum-beautify (TTY-safe interactive output). MCP: context7.