cross-validated-search

cross-validated-search is a skill for Claude Code, Codex from InternLM/WildClawBench. It costs 39 tokens per session (484 once invoked), scanned A, original, MIT.

A web-search and source-checking workflow for OpenClaw, an AI agent platform. It searches live pages, reads relevant sources, and checks whether specific claims are supported or contradicted.

In plain words
What is it for?
It can search the web, browse pages, verify individual claims, and produce evidence reports with source links and suggested next steps.
Why use it?
It helps distinguish evidence-backed information from unsupported or conflicting claims. That is useful when answers need current sources or explicit verification.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit It can search the web, browse pages, verify individual claims, and produce evidence reports with source links and suggested next steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/internlm/wildclawbench/openclaw-free-web-search
Install

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.

Any agent
npx skills add InternLM/WildClawBench --skill openclaw-free-web-search
Clone the repo
git clone --depth 1 https://github.com/InternLM/WildClawBench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for cross-validated-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/internlm/wildclawbench/openclaw-free-web-search/github.svg)](https://agentmods.dev/skills/internlm/wildclawbench/openclaw-free-web-search)
Your own site
<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.

agentmods 80×15 button for cross-validated-search

Your own site · 80×15
<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>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 5ef54e795b56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

skills/4/openclaw-free-web-search/SKILL.md · 60 lines

What it actually says

Cross-Validated Search for OpenClaw

This skill gives OpenClaw a practical verification workflow:

  • search-web for live search results
  • browse-page for reading the full content of a source
  • verify-claim for support/conflict classification
  • evidence-report for 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
  1. Run search-web for factual or recent questions.
  2. Use browse-page on the most relevant source when snippets are not enough.
  3. Use verify-claim when a concrete claim needs a support/conflict summary.
  4. Use evidence-report when you want a compact evidence package with citations and next steps.
  5. Use --deep when the claim matters enough to justify page-aware verification.
  6. Cite the returned URLs in the final answer.

What success looks like

  • the verdict is explicit
  • the result includes support and conflict scores
  • page_aware is true when deep verification ran
  • the recommended free path is ddgs + self-hosted searxng
  • source URLs are ready to cite

Limits

  • verify-claim is heuristic and evidence-aware, not a proof engine.
  • The default provider path is ddgs.
  • The recommended free upgrade path is self-hosted searxng via CROSS_VALIDATED_SEARCH_SEARXNG_URL.
  • Conflicting sources are surfaced, not automatically reconciled.

License

MIT License.

Files

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.

Changes

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.

  1. 10d ago First seen · 60 lines · 39 tokens per session scan A 5ef54e795b56

Subscribe to this mod's changes

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.

Related

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…

RTGS2017/NagaAgent · 108 tokens

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.

RTGS2017/NagaAgent · 0 tokens

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.

wshobson/agents · 51 tokens

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…

kirodotdev/KiroCrew · 105 tokens

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…

kirodotdev/KiroCrew · 90 tokens

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.

kirodotdev/KiroCrew · 47 tokens