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.
git clone --depth 1 https://github.com/wd041216-bit/zero-api-key-web-searchWrote 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/wd041216-bit/zero-api-key-web-search/gemini-extension)<a href="https://agentmods.dev/plugins/wd041216-bit/zero-api-key-web-search/gemini-extension"><img src="https://agentmods.dev/badge/plugins/wd041216-bit/zero-api-key-web-search/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/wd041216-bit/zero-api-key-web-search/gemini-extension"><img src="https://agentmods.dev/badge/plugins/wd041216-bit/zero-api-key-web-search/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
zero-api-key-web-search 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 25d 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": "zero-api-key-web-search",
"version": "21.0.0",
"description": "Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.",
"contextFileName": "GEMINI.md"
}
What ships with it
17 files beside gemini-extension.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.
- assets/agent-search-pipeline.svg 4.3 KB
- assets/architecture.png 5042 KB
- assets/banner.png 4879 KB
- assets/banner.svg 2.1 KB
- assets/benchmark-card.svg 1.9 KB
- assets/icon.png 13 KB
- assets/icon.svg 2.4 KB
- assets/social_square.png 4816 KB
- assets/terminal-demo.svg 2.4 KB
- assets/workflow.svg 2.4 KB
- examples/cli-quickstart.md 661 B
- examples/demo-transcript.md 1.6 KB
- examples/gemini.md 1.1 KB
- examples/openclaw.md 1.1 KB
- scripts/export_artifacts.sh 1.4 KB runs code
- scripts/start-searxng.sh 1.9 KB runs code
- scripts/validate-free-path.sh 2.3 KB runs code
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.
- 25d ago First seen · 7 lines scan A cdaee03ba009
zero-api-key-web-search is a plugin published in the GitHub repository wd041216-bit/zero-api-key-web-search (19 stars, last pushed 25d 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 2026-09-21.
Other plugins, from other repositories
lenz
Check the factual claims in a draft or an answer against independent sources: a quick verdict with a confidence for each claim, or a deep check that shows the key finding and its sources.
insaight
LinkedIn prospect intelligence inside Claude. Automates the research behind outreach, not the sending: classifies what people and companies post about, mines comment threads for warm leads, surfaces uncommon commonalities, and learns which hooks earn replies. 18 MCP tools plus 8 skills, all local.
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
maidan
Maidan MCP server - agent coordination for your own instance.
shotcut-mcp
Full transactional editor for Shotcut projects through a local MCP server.
todox
The log your next session resumes from: decisions, dead ends, handoffs and open tasks, shared across machines, agents and people over the todox MCP server. Reminds a session to read the log first and to write it up before finishing.