native-web-search

native-web-search is a skill for Claude Code, Codex from mitsuhiko/agent-stuff. It costs 24 tokens per session (340 once invoked), scanned A, original, Apache-2.0.

A command-line skill for quick internet research that returns a concise summary and the full web addresses of important sources.

In plain words
What is it for?
Use it to look up software releases, breaking changes, or other current topics and receive a sourced summary.
Why use it?
It saves time when an agent needs current information and source links for a technical task.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/mitsuhiko/agent-stuff/native-web-search
Any agent
npx skills add mitsuhiko/agent-stuff --skill native-web-search
Clone the repo
git clone --depth 1 https://github.com/mitsuhiko/agent-stuff

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 native-web-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/mitsuhiko/agent-stuff/native-web-search.svg)](https://agentmods.dev/skills/mitsuhiko/agent-stuff/native-web-search)
Your own site
<a href="https://agentmods.dev/skills/mitsuhiko/agent-stuff/native-web-search"><img src="https://agentmods.dev/badge/skills/mitsuhiko/agent-stuff/native-web-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 340 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00024 $0.00340
Opus 5 $0.00012 $0.00170
Sonnet 5 $0.00005 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 4d ago against content hash e6df83dde50d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

native-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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (search.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/native-web-search/SKILL.md · 50 lines

What it actually says

Use this skill to run a fast model with native web search enabled and get a concise research summary with explicit full URLs.

Script

  • search.mjs

Usage

Run from this skill directory:

node search.mjs "<what to search>" --purpose "<why you need this>"

Examples:

node search.mjs "latest python release" --purpose "update dependency notes"
node search.mjs "vite 7 breaking changes" --purpose "prepare migration checklist"

Optional flags:

  • --provider openai-codex|anthropic
  • --model <model-id>
  • --timeout <ms>
  • --json

Output expectations

The script instructs the model to:

  • search the internet for the requested topic
  • provide a concise summary for the given purpose
  • include full canonical URLs (https://...) for each key finding
  • highlight disagreements between sources

Notes

  • No extra npm install is required.
  • If module resolution fails, set PI_AI_MODULE_PATH to @earendil-works/pi-ai's dist/index.js path.
  • If OAuth helper resolution fails, set PI_AI_OAUTH_MODULE_PATH to @earendil-works/pi-ai's dist/oauth.js path.
  • For OAuth providers, the script can fall back to a still-valid cached access token from ~/.pi/agent/auth.json.
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. 4d ago First seen · 50 lines · 24 tokens per session scan A e6df83dde50d

Subscribe to this mod's changes

native-web-search is a skill published in the GitHub repository mitsuhiko/agent-stuff (3,044 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 340 once invoked, about $0.0001 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

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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