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.
npx agentmods add skills/ag2ai/ag2-assistant/web-researchnpx skills add ag2ai/ag2-assistant --skill web-researchgit clone --depth 1 https://github.com/ag2ai/ag2-assistantWrote 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.
[](https://agentmods.dev/skills/ag2ai/ag2-assistant/web-research)<a href="https://agentmods.dev/skills/ag2ai/ag2-assistant/web-research"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-assistant/web-research.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00045 | $0.00421 |
| Opus 5 | $0.00023 | $0.00211 |
| Sonnet 5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
web-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 6d 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.
What it actually says
Web research
A method for answering research questions well instead of from a single search.
Method
- Clarify the question. Identify exactly what's being asked and what a good answer looks like (a fact, a comparison, a recommendation, a summary).
- Search broadly, then narrow. Run more than one search with different phrasings. Don't stop at the first result — the first hit is often an ad, an SEO page, or out of date.
- Open the primary sources. Use the web-fetch tool to read the actual pages, not just search snippets. Prefer official docs, original reporting, primary data, and recent dates over aggregators.
- Cross-check. Confirm any important fact in at least two independent sources. If sources disagree, say so rather than picking one silently.
- Mind recency. For anything that changes over time (versions, prices, news, "latest"), check the publication date and prefer the most recent reliable source. Note the date in your answer.
Answering
- Lead with the direct answer, then the supporting detail.
- Cite sources — name the site/publication (and link if available) for each key claim so the user can verify.
- Distinguish what you're confident about from what's uncertain or contested.
- If you couldn't verify something, say "I couldn't confirm this" — don't guess.
Pitfalls
- One source ≠ a fact. Single-source claims are leads, not conclusions.
- Snippets lie / lack context — open the page.
- Stale results: a top result can be years old. Check dates.
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.
- 6d ago First seen · 41 lines · 45 tokens per session scan A 7fa501e5efbc
web-research is a skill published in the GitHub repository ag2ai/ag2-assistant (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 421 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…