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 javded-itres/Holix --skill web-researchergit clone --depth 1 https://github.com/javded-itres/HolixWrote 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/javded-itres/holix/web-researcher)<a href="https://agentmods.dev/skills/javded-itres/holix/web-researcher"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/web-researcher/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/javded-itres/holix/web-researcher"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/web-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00243 |
| Opus 5.5 | $0.00020 | $0.00097 |
| Sonnet 5.5 | $0.00010 | $0.00049 |
| Haiku 4.5 | $0.00005 | $0.00024 |
Grade A, and why
web-researcher 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 1mo 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
When to use
Only when the user explicitly requests the web_researcher sub-agent
(/subagent-spawn web_researcher …, "делегируй web_researcher", etc.).
Do not auto-spawn for ordinary search questions.
How to delegate
delegate_to_subagent(agent_type="web_researcher", task="<full user request>")wait_subagent_result(job_id="<returned job_id>")if the user wants the answer in this reply- Summarize the sub-agent response for the user
Task text
Include in task: what to find, geography/route, date (today), preferred sources, output format.
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.
- 1mo ago First seen · 30 lines · 50 tokens per session scan A 4f373673f8ae
web-researcher is a skill published in the GitHub repository javded-itres/Holix (19 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 243 once invoked, about $0.0002 per session on Opus 5.5. 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
animated-portfolio-sites
Build a one-page animated personal or portfolio site (canvas starfield, rotating galaxies with mouse parallax, hidden accordion/card content, anchor nav) and publish it free on GitHub Pages. Covers the canvas technique and the Pages permission wall, not just one task.
quartz-multilang-site-maintenance
Maintain and edit a Quartz static site (Quartz Syncer / quartz-site fork) that publishes to GitHub Pages — especially editing the 4-language home/index pages (pt-br/en/es/fr), cross-referencing sections, removing items, and verifying publication through the CDN/cache/redirect maze. Covers the two CLAUDE.md…
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
web-search-tool
Web search tool. Searches for information on the internet using the Brave Search API. Use when: Use when: researching the latest news, searching technical documentation, fact-checking, or retrieving a list of search results.
web-enumeration
Sensitive file scanning, path traversal bypass, vHost enum, .env extract, log mining, Varnish detect.
hunt-wordpress
Use when an authorized target exposes WordPress core, plugin, theme, REST, or XML-RPC behavior.