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 stellarshenson/claude-code-pluginsnpx agentmods add plugins/stellarshenson/claude-code-plugins/marketplacegit clone --depth 1 https://github.com/stellarshenson/claude-code-pluginsGrade A, and why
stellarshenson-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "stellarshenson-marketplace",
"owner": {
"name": "Stellars Henson",
"email": "[email protected]"
},
"metadata": {
"description": "Claude Code plugins for autonomous development workflows, critical analysis, data science standards, SVG infographics, document processing, and project journaling",
"version": "1.7.13",
"author": "stellarshenson"
},
"plugins": [
{
"name": "autobuild",
"source": "./plugins/autobuild",
"version": "1.7.13",
"description": "Autonomous build iteration orchestrator with multi-agent review, FSM-driven lifecycle, and YAML-configured workflows",
"keywords": [
"orchestrator",
"iteration",
"multi-agent",
"review",
"fsm",
"build"
],
"category": "development",
"tags": [
"autonomous",
"quality",
"workflow",
"agents"
]
},
{
"name": "devils-advocate",
"source": "./plugins/devils-advocate",
"version": "1.7.13",
"description": "Critical document analysis with persona-driven risk scoring, iterative scorecard evaluation, and versioned corrections - plus adversarial-review, hostile red-team review of code and artefacts with eleven pluggable expert adversaries",
"keywords": [
"critique",
"analysis",
"scorecard",
"risk",
"devil",
"advocate",
"adversarial-review",
"red-team"
],
"category": "documentation",
"tags": [
"review",
"quality",
"persona",
"evaluation",
"audit"
]
},
{
"name": "datascience",
"source": "./plugins/datascience",
"version": "1.7.13",
"description": "Data science project standards - notebook structure, rich output styling, copier scaffolding, and compliance review",
"keywords": [
"datascience",
"notebook",
"jupyter",
"rich"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.
- 2d ago First seen · 166 lines scan A bb2233b025d2
stellarshenson-marketplace is a plugin published in the GitHub repository stellarshenson/claude-code-plugins (3 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 2026-08-31.
Other plugins, from other repositories
example
Qwen-MM-Plugins example — a minimal template capability (skill + MCP server) demonstrating the three tool return shapes (text / image / frames); copy it to add your own.
skills
Agent Skills for Sonilo's licensed music, sound-effects, dubbing, and audio-ducking API — with structured-brief prompting guidance (pre-flight, music briefs, SFX action maps) folded into each skill.
nicknisi marketplace
Personal collection of Claude Code plugins for content creation, ideation, developer experience, image generation, and enhanced workflows.
comfyui-agent-kit marketplace
Local-first ComfyUI skills + the comfyui-mcp connection for Claude Code. The plugin form of ComfyUI-Agent-Kit, the local-first counterpart to the Comfy Cloud MCP.
vibe-replay marketplace
Turn AI coding sessions into animated, interactive web replays.
anycap
Multimodal capabilities for AI agents through the AnyCap CLI.