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 vakovalskii/searcharvester --skill searcharvester-deep-researchgit clone --depth 1 https://github.com/vakovalskii/searcharvesterWrote 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/vakovalskii/searcharvester/searcharvester-deep-research)<a href="https://agentmods.dev/skills/vakovalskii/searcharvester/searcharvester-deep-research"><img src="https://agentmods.dev/badge/skills/vakovalskii/searcharvester/searcharvester-deep-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/vakovalskii/searcharvester/searcharvester-deep-research"><img src="https://agentmods.dev/badge/skills/vakovalskii/searcharvester/searcharvester-deep-research.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 | $0.00107 | $0.03610 |
| Opus 5 | $0.00053 | $0.01805 |
| Sonnet 5 | $0.00021 | $0.00722 |
| Haiku 4.5 | $0.00011 | $0.00361 |
Grade A, and why
searcharvester-deep-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 12d 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 12d ago First seen · 428 lines · 107 tokens per session scan A 81d23d962e66
searcharvester-deep-research is a skill published in the GitHub repository vakovalskii/searcharvester (262 stars, last pushed 4mo ago), licensed AGPL-3.0. It adds 107 tokens to every session and 3,610 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 2026-08-30.
Other skills, from other repositories
humanizer
| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
wb_finance_skill
A general entry point for requests about finance, investing, markets, securities, funds, trading, financial reports, and related analysis.
humanizer_zh
A text editor that removes patterns commonly associated with AI-generated writing. It rewrites text to sound more natural and more like ordinary human writing.
multimodal_generation
A tool for generating 3D models from text or images and applying template-based video effects to images. It supports image effects such as an embrace, transformation, or objects turning to dust.
ardot_design_core
"Foundational workflow and hard rules shared by ALL Ardot canvas design tasks (UI screens, slides, posters, design systems, design-to-code). This skill carries the canvas schema, editing principles, the standard step-by-step workflow, visual style guide, and composite effects. It is injected automatically alongside a…
doc_typeset
A document layout tool that turns content and design settings into styled HTML. It includes templates for contracts, academic papers, official documents, business reports, meeting notes, research reports, and annual reports.