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 secondsky/claude-skillsnpx agentmods add plugins/secondsky/claude-skills/cloudflare-imagesgit clone --depth 1 https://github.com/secondsky/claude-skillsWrote 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/secondsky/claude-skills/cloudflare-images)<a href="https://agentmods.dev/plugins/secondsky/claude-skills/cloudflare-images"><img src="https://agentmods.dev/badge/plugins/secondsky/claude-skills/cloudflare-images.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
cloudflare-images 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": "cloudflare-images",
"description": "This skill should be used when the user asks to \"upload images to Cloudflare\", \"implement direct creator upload\", \"configure image transformations\", \"optimize WebP/AVIF\", \"create image variants\", \"generate signed URLs\", \"add image watermarks\", \"integrate with Next.js/Remix\", \"configure webhooks\", \"debug CORS errors\", \"troubleshoot error 5408/9401-9413\", or \"build responsive images with Cloudflare Images API\".",
"version": "3.8.0",
"author": {
"name": "Claude Skills Maintainers",
"email": "[email protected]"
},
"license": "MIT",
"repository": "https://github.com/secondsky/claude-skills",
"keywords": [
"cloudflare-images",
"cloudflare",
"images",
"workers",
"edge",
"wrangler",
"avif",
"cors",
"webp",
"webhooks"
],
"agents": [
"./agents/optimization-agent.md",
"./agents/troubleshooting-agent.md",
"./agents/upload-workflow-agent.md"
],
"commands": [
"./commands/check-images.md",
"./commands/generate-variant.md",
"./commands/validate-config.md"
]
}
What it installs
The manifest is a name and a version. 1 skill, 3 commands, 3 agents travel with it, and installing the plugin installs all of them — 407 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cloudflare-images A 104 tokens
- Command cloudflare-images:generate-variant A 48 tokens
- Command cloudflare-images:validate-config A 43 tokens
- Command cloudflare-images:check A 37 tokens
- Agent upload-workflow-agent A 55 tokens
- Agent optimization-agent A 54 tokens
- Agent troubleshooting-agent A 66 tokens
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 · 34 lines scan A 3b15e3e4ff34
cloudflare-images is a plugin published in the GitHub repository secondsky/claude-skills (214 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
chamnan
Makes a repository know itself and preserve the engineering context built while you work with it, so an agent stops rediscovering both. An architecture index and an impact map instead of scanning files; work state, session records and the decisions behind them instead of losing context between sessions; the procedures.
fewword
Context engineering plugin - tiered offloading, smart summaries, secret redaction, TOML/JSON config, command aliases, MCP allowlists, and self-diagnostics.
hyperfocus
ADHD-friendly output formatting. Restructures responses with evidence-based cognitive accessibility: chunking, visual hierarchy, front-loaded key points, and progressive disclosure.
harnessay
Profile your Claude Code transcripts: context budget report, skill-promotion candidates, and a skill regression test harness. Local-only, stdlib-only.
ccx
Scratch-notebook context management for any project: per-thread STATE.md handoff docs with one-command create-or-resume (/ccx:start-thread), a compiled parallel-session-safe INDEX dashboard that recompiles itself on every STATE write (/ccx:save-state · /ccx:tidy-scratch), a Stop-hook freshness guard so working state…
project-manager
Turns a vague project idea into a developer-ready requirements spec and a vertical-slice build plan by interviewing you one question at a time.