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 CyranoB/web-foragernpx agentmods add plugins/cyranob/web-forager/forager-skillsgit clone --depth 1 https://github.com/CyranoB/web-foragerWrote 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/cyranob/web-forager/forager-skills)<a href="https://agentmods.dev/plugins/cyranob/web-forager/forager-skills"><img src="https://agentmods.dev/badge/plugins/cyranob/web-forager/forager-skills.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
forager-skills 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.
What it actually says
{
"name": "forager-skills",
"description": "Seven research skills powered by DuckDuckGo search and Jina Reader: article auditing, web research, fact-checking, news monitoring, competitive intelligence, technology evaluation, and geopolitical analysis",
"source": "./",
"strict": false,
"skills": [
"./skills/article-audit",
"./skills/deep-research",
"./skills/fact-check",
"./skills/news-monitor",
"./skills/competitive-intel",
"./skills/tech-advisor",
"./skills/geopolitical-analyst"
],
"version": "1.1.1",
"author": {
"name": "CyranoB"
},
"homepage": "https://github.com/CyranoB/web-forager",
"repository": "https://github.com/CyranoB/web-forager",
"license": "MIT",
"keywords": [
"search",
"news",
"research",
"fact-check",
"geopolitics",
"web-forager"
]
}What it installs
The manifest is a name and a version. 7 skills travel with it, and installing the plugin installs all of them — 282 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
2 files beside marketplace.json#forager-skills 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.
- today Changed 931dc933337f
- yesterday First seen · 30 lines scan A f81acd67db28
forager-skills is a plugin published in the GitHub repository CyranoB/web-forager (10 stars, last pushed today), 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 2026-09-04.
Other plugins, from other repositories
jail-search
Search a billion+ documents — papers, books, code, legal cases, forums, Wikipedia, and more.
mixedbread-parsing
Parse documents, extract structured content, and run OCR using the Mixedbread Parsing API.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.
claude-webcache
Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 minutes — claude-webcache makes them persist.
wikimoth
Deterministic, token-minimal memory for Claude Code: capture each session as a [[wikilink]] note (edges computed by code, not a model) and recall connected notes at boot.
youtube-outlier-research
YouTube outlier finder and competitor research. Ranks a channel's recent uploads and Shorts by how far each beat that channel's own baseline views, compares channels, and sweeps a niche for video ideas that already worked. Runs on your own free YouTube Data API key, unmetered.