networked-research

networked-research is a skill for Claude Code, Codex from tao12345666333/ankaloop. It costs 69 tokens per session (285 once invoked), scanned A, original, Apache-2.0.

A guide for researching current information on the live web, including documentation, APIs, libraries, examples, and breaking changes. It explains when to search and when to fetch a known page.

In plain words
What is it for?
Use it to find unfamiliar technologies, consult current official documentation, check release changes, and gather implementation examples from online sources.
Why use it?
It helps an agent avoid relying on outdated knowledge when the needed technical information may have changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find unfamiliar technologies, consult current official documentation, check release changes, and gather implementation examples from online sources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tao12345666333/ankaloop/networked-research
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 tao12345666333/ankaloop --skill networked-research
Clone the repo
git clone --depth 1 https://github.com/tao12345666333/ankaloop

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 networked-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/tao12345666333/ankaloop/networked-research/github.svg)](https://agentmods.dev/skills/tao12345666333/ankaloop/networked-research)
Your own site
<a href="https://agentmods.dev/skills/tao12345666333/ankaloop/networked-research"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/networked-research/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 networked-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/tao12345666333/ankaloop/networked-research"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/networked-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 285 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 $0.00069 $0.00285
Opus 5 $0.00034 $0.00143
Sonnet 5 $0.00014 $0.00057
Haiku 4.5 $0.00007 $0.00028

Measured 11d ago against content hash adb35faf763b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

networked-research 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 11d 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.

src/ankaloop/builtin_skills/networked-research/SKILL.md · 29 lines

What it actually says

Networked Research

Use live web access when local context is not enough.

Prefer the built-in web tools

  • Use web_search for internet discovery, current docs, release notes, API references, and unknown technologies.
  • Use web_fetch to read a specific URL after you already know the page you need.
  • These tools work out of the box and do not require the user to configure a search MCP server.

When to search vs fetch

  • Search first when the exact page is unknown.
  • Fetch directly when the user gives you a URL or when search already surfaced the right page.
  • After searching, fetch the most relevant result if you need details rather than snippets.

Working style

  1. Search with a focused query.
  2. Narrow by domain when the user wants official docs or a known website.
  3. Fetch the most relevant page or pages.
  4. Base your answer or implementation on the fetched content, not on stale model memory.
  5. Mention uncertainty if the web results conflict or look incomplete.
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. 11d ago First seen · 29 lines · 69 tokens per session scan A adb35faf763b

Subscribe to this mod's changes

networked-research is a skill published in the GitHub repository tao12345666333/ankaloop (48 stars, last pushed 12d ago), licensed Apache-2.0. It adds 69 tokens to every session and 285 once invoked, about $0.0003 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.