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 davistroy/claude-marketplacenpx agentmods add plugins/davistroy/claude-marketplace/personal-plugingit clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/personal-plugin)<a href="https://agentmods.dev/plugins/davistroy/claude-marketplace/personal-plugin"><img src="https://agentmods.dev/badge/plugins/davistroy/claude-marketplace/personal-plugin.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
personal-plugin 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 4d 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.
What it actually says
{
"name": "personal-plugin",
"description": "Personal Claude Code commands and skills for documentation review, architecture analysis, git workflows, document processing, and multi-source research",
"version": "11.10.0",
"author": {
"name": "Troy Davis",
"email": "[email protected]"
},
"homepage": "https://github.com/davistroy/claude-marketplace",
"repository": "https://github.com/davistroy/claude-marketplace",
"license": "MIT",
"keywords": [
"personal",
"automation",
"research",
"llm-orchestration"
]
}
What it installs
The manifest is a name and a version. 29 skills, 23 commands, 10 agents, 2 hooks travel with it, and installing the plugin installs all of them — 2,809 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill accessibility-annotator A 90 tokens
- Skill evaluate-pipeline-output A 71 tokens
- Skill lab-notebook A 104 tokens
- Skill create-wiki A 105 tokens
- Skill security-analysis A 61 tokens
- Skill ship A 40 tokens
- Skill task-sync A 169 tokens
- Skill visual-explainer A 49 tokens
- Skill wiki A 60 tokens
- Skill arch-review A 47 tokens
- Skill leak-risk-audit A 35 tokens
- Skill plan-gate A 78 tokens
- Skill prime A 63 tokens
- Skill release-plugin A 35 tokens
- Skill spark-recon A 84 tokens
- Skill summarize-feedback A 46 tokens
- Skill archive-project A 78 tokens
- Skill clear-prep A 114 tokens
- Skill new-project A 77 tokens
- Skill spark-audit A 49 tokens
- Skill spec-to-prototype A 106 tokens
- Skill brain-entry A 65 tokens
- Skill ultra-plan A 52 tokens
- Skill research-topic B 66 tokens
- Skill fleet-health B 126 tokens
- Skill jetson-audit B 54 tokens
- Skill unlock B 43 tokens
- Skill explain-project C 125 tokens
- Skill jetson-recon D 105 tokens
- Command implement-plan A 19 tokens
- Command plan-improvements A 12 tokens
- Command create-plan A 22 tokens
- Command validate-plugin A 21 tokens
- Command ask-questions A 8 tokens
- Command assess-document A 7 tokens
- Command consolidate-documents A 17 tokens
- Command develop-image-prompt A 14 tokens
- Command finish-document A 15 tokens
- Command new-skill A 14 tokens
- Command review-arch A 15 tokens
- Command review-intent A 12 tokens
- Command analyze-transcript A 6 tokens
- Command clean-repo A 10 tokens
- Command define-questions A 9 tokens
- Command remove-ip A 17 tokens
- Command scaffold-plugin A 14 tokens
- Command test-project A 31 tokens
- Command plan-next A 8 tokens
- Command bump-version A 12 tokens
- Command arch-synthesize A 25 tokens
- Command arch-review-single A 15 tokens
- Command convert-markdown B 11 tokens
- Agent performance-engineer A 25 tokens
- Agent platform-engineer A 29 tokens
- Agent qa-architect A 23 tokens
- Agent security-architect A 29 tokens
- Agent software-engineer A 26 tokens
- Agent data-architect A 27 tokens
- Agent integration-architect A 27 tokens
- Agent risk-compliance A 27 tokens
- Agent solutions-architect A 35 tokens
- Agent sre-operator B 30 tokens
- Hook PreToolUse A not measured
- Hook SessionStart A 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.
- 4d ago First seen · 19 lines scan A 5a7adf06aa95
personal-plugin is a plugin published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d 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
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.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
mattpocock-skills
Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.