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 | $0.00025 | $0.00121 |
| Sonnet 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 10d 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.
- 10d 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 (14 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 243 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
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-enumeration
Sensitive file scanning, path traversal bypass, vHost enum, .env extract, log mining, Varnish detect.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
hunt-wordpress
Use when an authorized target exposes WordPress core, plugin, theme, REST, or XML-RPC behavior.