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 InternLM/WildClawBench --skill openclaw-free-web-searchgit clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/openclaw-free-web-search)<a href="https://agentmods.dev/skills/internlm/wildclawbench/openclaw-free-web-search"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/openclaw-free-web-search/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/internlm/wildclawbench/openclaw-free-web-search"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/openclaw-free-web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00484 |
| Opus 5 | $0.00019 | $0.00242 |
| Sonnet 5 | $0.00008 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
cross-validated-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 10d 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
Cross-Validated Search for OpenClaw
This skill gives OpenClaw a practical verification workflow:
search-webfor live search resultsbrowse-pagefor reading the full content of a sourceverify-claimfor support/conflict classificationevidence-reportfor a citation-ready summary with next steps
Install
pip install cross-validated-search
Minimum verification
search-web "OpenAI API pricing" --type news --timelimit w
verify-claim "Python 3.13 is the latest stable release" --deep --max-pages 2 --json
evidence-report "Python 3.13 stable release" --claim "Python 3.13 is the latest stable release" --deep --json
Recommended flow
- Run
search-webfor factual or recent questions. - Use
browse-pageon the most relevant source when snippets are not enough. - Use
verify-claimwhen a concrete claim needs a support/conflict summary. - Use
evidence-reportwhen you want a compact evidence package with citations and next steps. - Use
--deepwhen the claim matters enough to justify page-aware verification. - Cite the returned URLs in the final answer.
What success looks like
- the verdict is explicit
- the result includes support and conflict scores
page_awareis true when deep verification ran- the recommended free path is
ddgs + self-hosted searxng - source URLs are ready to cite
Limits
verify-claimis heuristic and evidence-aware, not a proof engine.- The default provider path is
ddgs. - The recommended free upgrade path is self-hosted
searxngviaCROSS_VALIDATED_SEARCH_SEARXNG_URL. - Conflicting sources are surfaced, not automatically reconciled.
License
MIT License.
What ships with it
1 file beside SKILL.md 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.
- 10d ago First seen · 60 lines · 39 tokens per session scan A 5ef54e795b56
cross-validated-search is a skill published in the GitHub repository InternLM/WildClawBench (519 stars, last pushed 24d ago), licensed MIT. It adds 39 tokens to every session and 484 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 2026-08-30.
Other skills, from other repositories
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
travel-explore
You are a network explorer on a travel adventure. Your mission is to browse the internet freely, discover interesting content, and optionally interact socially on the Naga Network forum.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-auth
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.