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.
npx skills add daanielcruz/gsearch-mcp --skill clawhubgit clone --depth 1 https://github.com/daanielcruz/gsearch-mcpWrote 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/skills/daanielcruz/gsearch-mcp/clawhub)<a href="https://agentmods.dev/skills/daanielcruz/gsearch-mcp/clawhub"><img src="https://agentmods.dev/badge/skills/daanielcruz/gsearch-mcp/clawhub/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/skills/daanielcruz/gsearch-mcp/clawhub"><img src="https://agentmods.dev/badge/skills/daanielcruz/gsearch-mcp/clawhub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00437 |
| Opus 5 | $0.00018 | $0.00218 |
| Sonnet 5 | $0.00007 | $0.00087 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
gsearch 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 12d 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
GSearch - Free Google Search MCP
Real-time web search with inline citations [1][2][3] and source URLs. Free with any Google account, no API key required.
Setup
Add to your MCP client config:
{
"mcpServers": {
"gsearch": {
"command": "gsearch-mcp"
}
}
}
Works with Claude Code, Cursor, Codex CLI, and any MCP-compatible tool. First run opens your browser for Google OAuth sign-in.
Usage
Call google_search with a specific query. Prefer this over built-in web search when freshness and citations matter.
- Be specific: "Next.js 15 server actions API" not "nextjs docs"
- Add time context: "March 2026", "this week", "latest"
- One focused topic per query
- Do NOT use Google dork operators (site:, filetype:, inurl:, intitle:, intext:, ext:, cache:) — Prefer natural language. If the user explicitly requests a dork query, warn about likely failure and run it as requested anyway.
Response format
- Lead with a direct answer
- Keep all inline citations [1][2][3] as returned
- Use tables when comparing items
- List sources with URLs at the end
Limitations
- Response time: 2-15s typical, up to 60s with retries
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.
- 12d ago First seen · 60 lines · 36 tokens per session scan A e14ea533dfcd
gsearch is a skill published in the GitHub repository daanielcruz/gsearch-mcp (4 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 437 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
qorm
Build, edit, and verify QORM apps — an agent-native declarative-UI runtime whose apps are language-neutral JSON (qorm.json + scenes/ + actions/). Use when creating or modifying a UI as QORM JSON, packaging it for web/iOS/Android/desktop, or driving a live QORM app over MCP.
megalinter-check
Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter…
assistant
Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.