A procedure for searching the web and fetching pages through the TinyFish command-line tool. It explains how to check installation and authentication, then choose a search or page-fetch method.

Researching current facts, public tools, and external systems, then reading information from web pages.

It provides a defined way to ground answers in current public information instead of relying only on existing knowledge. It also stops when the required tool or login is unavailable.

web-search — Skill for Claude Code and Codex by ntorga

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 ntorga/agent-starter-kit --skill web-search

Clone the repo

git clone --depth 1 https://github.com/ntorga/agent-starter-kit

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/ntorga/agent-starter-kit/web-search/github.svg)](https://agentmods.dev/skills/ntorga/agent-starter-kit/web-search)

Your own site

<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/web-search"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/web-search"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 913 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00913
Opus 5	$0.00007	$0.00456
Sonnet 5	$0.00003	$0.00183
Haiku 4.5	$0.00001	$0.00091

Measured 2d ago against content hash 5fa603e0a153, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade A, and why

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 2d 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/web-search/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Answers about current facts, public tools, and external systems need web grounding. Search finds pages. Fetch reads them. Search runs through the TinyFish CLI. Page fetch tries the host's native web fetch tool first and falls back to the TinyFish CLI when the native tool is blocked. This skill defines when to use each surface, the exact commands, and how to read the output. Full flag reference: https://docs.tinyfish.ai/cli/commands

Procedure

Verify the tool is installed

Check for the CLI. Run command -v tinyfish. If it is missing, stop and tell the user:
- The TinyFish CLI is required for web search and fetch.
- Install it by following https://docs.tinyfish.ai/cli/commands.
- It is free, but it requires an API key — the user creates one and completes login with tinyfish auth login themselves. Do not install the tool or run tinyfish auth login on your own. Once the user confirms setup, continue.
Check authentication. Run tinyfish auth status. If it reports no valid key, tell the user to run tinyfish auth login themselves and stop. Do not run tinyfish auth login or tinyfish auth set on your own.

Choose the surface

Answer from local context first. Use project files and the conversation when they hold the answer. Skip the web when the question is about this codebase.
Search when the right page is unknown. Use search for "what is", "how does", and "compare" questions, and for anything time-sensitive: versions, releases, prices, news.
Fetch when the page is known. Try the host's native web fetch tool first. Fall back to tinyfish fetch content get when the native tool is blocked, fails, or returns empty content.

Search

Run the search:

tinyfish search query "best React state management libraries"

Add hints when the question is geo- or language-specific:

tinyfish search query "best pho in Saigon" --location "Vietnam" --language "en"

Read the full file on GitHub · 72 lines

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.

2d ago First seen · 72 lines · 14 tokens per session scan A 5fa603e0a153

Subscribe to this mod's changes

web-search is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 913 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 2026-09-13.

Multi-Agent Research agent-framework ai-agents coding-assistant llm-orchestration model-agnostic

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

python-package-management

Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.

microsoft/agent-framework · 43 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

web-search