A web-search skill that selects an available hosted or local search provider and falls back to Serper when needed. It is used to find information on the internet rather than search files in the project.

Use it when a user asks for web research and no direct web-search tool is already available.

It gives the agent a defined search path and avoids inventing results when no search service is configured.

websearch — Skill for Claude Code and Codex by gabrielmoreira

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 gabrielmoreira/agent-skills-mirror --skill websearch

Clone the repo

git clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirror

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/websearch/github.svg)](https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/websearch)

Your own site

<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/websearch"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/websearch/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/websearch"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/websearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 431 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.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00431
Opus 5.5	$0.00022	$0.00172
Sonnet 5.5	$0.00011	$0.00086
Haiku 4.5	$0.00006	$0.00043

Measured 9d ago against content hash 090f13cc8412, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

websearch 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 9d 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.

Origin

This is a copy

100% identical to websearch — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

mirrors/repos/7df-lab@claw-code-rust/crates/skills/assets/bundled/websearch/SKILL.md · 48 lines

What it actually says

Web Search

Prefer Devo's built-in search. Use this skill only when you cannot call a model-facing web_search tool directly.

Preference order

Provider-hosted or local web_search tool — if your tool list includes web_search, call that tool. Do not route through this skill.
This skill — tries host web.search (local Exa / Tavily when configured), then Serper if a key is saved.
If nothing is configured — tell the user how to enable search (below). Do not invent results.

Enable hosted search (preferred)

Provider-hosted: set [tools.web_search] mode = "provider" and use a model on Anthropic Messages or OpenAI Responses that supports hosted search.
Local Exa / Tavily: set [tools.web_search] mode = "local" and configure a provider under [tools.web_search.local_providers.<id>] with kind = "exa" or kind = "tavily" (credentials via /login / auth.json).

Serper fallback (third party)

Only when hosted search is not available:

Get a free API key at https://serper.dev
In Devo, run /login → MCP Connections → Serper (web search) and paste the key.

Do not ask the user to set environment variables.

Optional overrides:

DEVO_WEBSEARCH_TIMEOUT — HTTP timeout in seconds (default 45).
DEVO_WEBSEARCH_NUM_RESULTS — organic results to return (default 5).

Usage

print(await websearch.run("latest Devo release"))

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.

9d ago First seen · 48 lines · 56 tokens per session scan A 090f13cc8412

Subscribe to this mod's changes

websearch is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (19 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 431 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to websearch, differing in 0 lines, and is treated as a copy.

Research

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens