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 kevinnft/ai-agent-skills --skill tinyfish-integrationgit clone --depth 1 https://github.com/kevinnft/ai-agent-skillsWrote 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/kevinnft/ai-agent-skills/tinyfish-integration)<a href="https://agentmods.dev/skills/kevinnft/ai-agent-skills/tinyfish-integration"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/tinyfish-integration/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/kevinnft/ai-agent-skills/tinyfish-integration"><img src="https://agentmods.dev/badge/skills/kevinnft/ai-agent-skills/tinyfish-integration.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 | $0.00022 | $0.01459 |
| Opus 5 | $0.00011 | $0.00730 |
| Sonnet 5 | $0.00004 | $0.00292 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
tinyfish-integration 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TinyFish Integration
TinyFish is a web toolkit for AI agents that provides search, fetch, and browser automation capabilities. Search and fetch are free for every account — no credits, no cost.
Available Tools
tinyfish_search
Search the live web and get structured, agent-ready results.
Use cases:
- Current information, news, prices
- Finding URLs before fetching content
- Anything that changes over time
Parameters:
query(required): Search query stringlocation(optional): 2-letter country code (e.g., "US", "FR", "ID")language(optional): 2-letter language code (e.g., "en", "fr", "id")page(optional): Page number for pagination (default: 0)
Example:
tinyfish_search(query="Hermes Agent AI", location="US", language="en")
Response format:
{
"results": [
{
"title": "Page Title",
"url": "https://example.com",
"snippet": "Description text...",
"site_name": "Example Site"
}
]
}
tinyfish_fetch
Pull the full content of any web page as clean extracted text.
Use cases:
- Reading articles, docs, product pages
- Extracting content without ads/navigation
- Batch processing multiple URLs (max 10)
Parameters:
urls(required): Single URL or comma-separated list (max 10)
Examples:
# Single URL
tinyfish_fetch(urls="https://example.com")
# Multiple URLs
tinyfish_fetch(urls="https://site1.com, https://site2.com, https://site3.com")
Response format:
{
"results": [
{
"url": "https://example.com",
"final_url": "https://example.com",
"title": "Page Title",
"description": "Meta description",
"language": "en",
"text": "# Heading\n\nClean extracted content..."
}
],
"errors": []
}
Setup
1. Get API Key
Visit https://agent.tinyfish.ai/api-keys to get your API key.
2. Configure Hermes
Add to ~/.hermes/.env:
TINYFISH_API_KEY=sk-tinyfish-YOUR_KEY_HERE
What ships with it
3 files 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 · 213 lines · 22 tokens per session scan A a5a3fd257e8b
tinyfish-integration is a skill published in the GitHub repository kevinnft/ai-agent-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,459 once invoked, about $0.0001 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
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
ketch
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y'…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
web-browse
Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.
agent-browser
Drive a real headless Chromium on the workspace host to read pages, fill forms, click buttons, run JS, and take screenshots. Use this whenever you need more than a plain HTTP fetch — pages that require JS to render, pages with an interactive element you have to click through, or when you want an accessibility-tree…
read-deleted-pages
Recover deleted, edited or historical web content using the Wayback Machine and its CDX API, archive.today, Common Crawl and Memento/Timetravel. Use when a page is deleted, changed or 404s, checking what a site used to say, finding old team or staff pages, prior pricing, removed posts, pre-redaction wording or old…