web-research

web-research is a skill for Claude Code, Codex from duyet/oma. It costs 91 tokens per session (805 once invoked), scanned A, original, Apache-2.0.

A guide for researching questions on the public internet and returning answers supported by checked sources. It recommends narrowing the question, reading full pages, preferring original sources, and cross-checking important claims.

In plain words
What is it for?
Use it to investigate current versions, prices, compatibility, documentation, standards, or other questions requiring verified web information.
Why use it?
It reduces the risk of relying on incomplete search snippets or an unsupported first result, especially for facts that may change.

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/duyet/oma/web-research
Any agent
npx skills add duyet/oma --skill web-research
Clone the repo
git clone --depth 1 https://github.com/duyet/oma

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 web-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/duyet/oma/web-research.svg)](https://agentmods.dev/skills/duyet/oma/web-research)
Your own site
<a href="https://agentmods.dev/skills/duyet/oma/web-research"><img src="https://agentmods.dev/badge/skills/duyet/oma/web-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 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 $0.00091 $0.00805
Opus 5 $0.00046 $0.00402
Sonnet 5 $0.00018 $0.00161
Haiku 4.5 $0.00009 $0.00081

Measured 3d ago against content hash 7ef8fc327252, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

examples/skills/web-research/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

web-research

The goal is a defensible answer, not the first plausible link. A single source is a claim; two independent sources agreeing is evidence. Your job is to turn a question into a small set of trustworthy findings, each traceable to where it came from.

Use the web_search tool to find sources and web_fetch to read them in full — snippets lie by omission; open the page before you quote it.

Loop

  1. Sharpen the question. What exact fact settles it? "Is library X compatible with Y" → "does X's docs/changelog list Y support, and as of which version". A vague question yields vague searches.
  2. Search deliberately. Start broad to map the terrain, then narrow with specific terms, error strings, version numbers, or site: filters. Rephrase when results are thin — different words surface different sources. Prefer the primary source: official docs, the changelog, the standard, the paper, the vendor's own page — over a blog summarizing it.
  3. Open and read. web_fetch the promising results. Read enough to confirm the claim in context, not just a matching sentence.
  4. Cross-check. Confirm anything load-bearing against a second independent source. Two blogs both citing the same original are one source. Watch for an answer that everyone copied from one wrong post.
  5. Synthesize with citations. Answer the question directly, then support it with links. Note your confidence and any disagreement you found.

Judging a source

  • Primary > secondary > hearsay. Docs and specs beat a tutorial; a tutorial beats a forum guess.
  • Check the date. Software, prices, and events go stale fast. An accurate 2021 answer can be wrong today. Prefer dated pages; state the date you relied on. Beware undated posts and content-farm SEO pages.
  • Who benefits. A vendor comparing itself to a rival, an affiliate "best of" list, marketing dressed as a benchmark — read for bias, corroborate elsewhere.
  • Watch versions. "How to do X" often changes between major versions. Match the answer to the version the user is on.

Read the full file on GitHub · 64 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.

  1. 3d ago First seen · 64 lines · 91 tokens per session scan A 7ef8fc327252

Subscribe to this mod's changes

web-research is a skill published in the GitHub repository duyet/oma (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 91 tokens to every session and 805 once invoked, about $0.0005 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 2026-08-31.

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