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 skills add jezweb/vite-flare-starter --skill web-researchgit clone --depth 1 https://github.com/jezweb/vite-flare-starterWrote 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/jezweb/vite-flare-starter/web-research)<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/web-research"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/web-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.
<a href="https://agentmods.dev/skills/jezweb/vite-flare-starter/web-research"><img src="https://agentmods.dev/badge/skills/jezweb/vite-flare-starter/web-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 42 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00050 | $0.00526 |
| Opus 5 | $0.00025 | $0.00263 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00053 |
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research
When to use
The user wants to learn about something that requires up-to-date information from multiple sources. Examples:
- "Research the latest changes to X"
- "What's the current state of Y?"
- "Find me information about Z"
Steps
-
Plan — break the topic into 2-4 specific search queries that cover different angles. Don't search the same thing multiple ways.
-
Search — run
web_searchfor each query (one at a time). Aim for 5-10 results each. Skim the snippets to identify the most authoritative sources. -
Read — for the 3-5 most promising results, call
browser_markdownto get the full content. Prefer official docs, well-known publications, and primary sources over aggregators or content farms.When deciding which sources to trust, consult
references/source-trust-heuristics.md(useread_skill_resourcewithpath: "references/source-trust-heuristics.md"). It lists high/medium/low trust tiers and red flags. -
Synthesise — write a structured summary that:
- Opens with a 1-2 sentence direct answer to the user's question
- Has 3-5 sections covering the key aspects
- Cites specific sources inline using markdown links:
[Source Title](url) - Notes any conflicts or uncertainty between sources
- Ends with "Sources" listing all URLs used
-
Offer next steps — use
offer_choicesto suggest follow-ups like "Dig deeper into X", "Compare with Y", "Find recent updates", or "Save this research as a file".
Style
- Be concise. Aim for 200-400 words of summary, not a wall of text.
- Use bullet points and short paragraphs.
- Cite as you go, not in a single block at the end (unless that's all the user wants).
- If sources disagree, say so explicitly — don't paper over it.
What not to do
- Don't make up facts. If a search returns nothing useful, say so and ask for clarification.
- Don't quote large blocks from sources — paraphrase and link.
- Don't assume one source is authoritative without checking another.
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.
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.
- 9d ago First seen · 43 lines · 50 tokens per session scan A 0ccbe614efab
web-research is a skill published in the GitHub repository jezweb/vite-flare-starter (48 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 526 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.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…