TinyFish Cookbook is a collection of example applications, recipes, and automations built with TinyFish, a web service that lets AI agents search the live web, read pages, and perform browser-based tasks. Developers use it to learn how to build web agents and connect them with workflows such as research, monitoring, and data collection. The catalogue entries provide agent skills and integrations for working with these examples and TinyFish endpoints.
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 tinyfish-io/tinyfish-cookbook --skill summer-school-findergit clone --depth 1 https://github.com/tinyfish-io/tinyfish-cookbookWrote 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/tinyfish-io/tinyfish-cookbook/summer-school-finder)<a href="https://agentmods.dev/skills/tinyfish-io/tinyfish-cookbook/summer-school-finder"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/summer-school-finder/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/tinyfish-io/tinyfish-cookbook/summer-school-finder"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/summer-school-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00137 | $0.01625 |
| Opus 5 | $0.00068 | $0.00813 |
| Sonnet 5 | $0.00027 | $0.00325 |
| Haiku 4.5 | $0.00014 | $0.00162 |
Grade A, and why
summer-school-finder 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summer School Finder
Given a program type, target age, location, and duration preference, find and compare real summer school programs from official university websites using parallel TinyFish agents.
Pre-flight check
tinyfish --version
tinyfish auth status
If not installed: npm install -g tinyfish
If not authenticated: tinyfish auth login
Step 1 — Clarify inputs
Collect the following before searching. Ask for any that are missing:
- Program type / subject — e.g. "Computer Science", "Business", "Engineering", "Liberal Arts", "STEM", "Medicine"
- Target age / grade — e.g. "high school students (Grade 10-12)", "undergraduates", "ages 14-17"
- Location — e.g. "USA", "UK", "Singapore", "Europe", "online"
- Duration — e.g. "2 weeks", "1 month", "Summer 2025/2026" (default to Summer 2026 if not specified)
If any are missing, use sensible defaults and state them upfront.
Step 2 — Discover program URLs
Before firing TinyFish agents, use your knowledge + a quick web search to identify 7-8 real, specific program page URLs from different universities that match the criteria.
Rules for URL discovery:
- Each URL must be from a different institution — no duplicates
- Use direct program pages, not search results or aggregator sites
- Prioritise well-known universities and established programs
- Mix large universities and smaller institutions
- Include variety: residential, online, hybrid formats where available
- Only include URLs you are confident actually exist
Example for "Computer Science, high school students, USA, Summer 2026":
https://summerprogram.stanford.eduhttps://summer.harvard.edu/high-schoolhttps://precollege.syr.eduhttps://summerdiscovery.com/michigan- etc.
Produce exactly 7-8 URLs then proceed to Step 3.
Step 3 — Parallel scraping
Fire one TinyFish agent per URL, all simultaneously using & + wait.
Use this goal prompt for every agent (substituting the actual values):
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 · 197 lines · 137 tokens per session scan A 5a1a188b6292
summer-school-finder is a skill published in the GitHub repository tinyfish-io/tinyfish-cookbook (2,155 stars, last pushed 8d ago), licensed MIT. It adds 137 tokens to every session and 1,625 once invoked, about $0.0007 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
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
surprise-me
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for…
build-monetized-app
Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…