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 cloudflare/skillsnpx agentmods add plugins/cloudflare/skills/marketplacegit clone --depth 1 https://github.com/cloudflare/skillsGrade A, and why
cloudflare 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
{
"$schema": "https://code.claude.com/schemas/marketplace.json",
"name": "cloudflare",
"owner": {
"name": "Cloudflare",
"url": "https://workers.cloudflare.com"
},
"plugins": [
{
"name": "cloudflare",
"source": "./",
"description": "Skills for the Cloudflare developer platform"
}
]
}
What ships with it
1 file beside marketplace.json 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 · 16 lines scan A d2c363fec613
cloudflare is a plugin published in the GitHub repository cloudflare/skills (2,744 stars, last pushed 24d ago), licensed Apache-2.0. 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
developer-kit-ai
AI/ML capabilities including prompt engineering, RAG, and chunking strategies.
contentful
Agent skills for Contentful apps, APIs, migrations, and personalization.
opentikz
TikZ resources for academic conceptual diagrams.
market-intelligence
Competitive landscape, incentive mapping, positioning, and information asymmetry — strategic-group mapping with mobility-barrier analysis, incentive-driven behavior prediction, positioning trade-off discipline, information-asymmetry analysis, and game-theory-grounded competitive response forecasting.
consulting
Strategic narrative, hypothesis-driven problem solving, and deliverable craft — Minto pyramid structure, hypothesis trees, hypothesis-driven workplans, deck outlines, exec memos, so-what sharpening, and doc/deck review.
capacitor-core
Core Capacitor skills for best practices, plugin selection, and MCP automation.