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 hackathon-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/hackathon-finder)<a href="https://agentmods.dev/skills/tinyfish-io/tinyfish-cookbook/hackathon-finder"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/hackathon-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/hackathon-finder"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/hackathon-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 | $0.00110 | $0.02752 |
| Opus 5.5 | $0.00044 | $0.01101 |
| Sonnet 5.5 | $0.00022 | $0.00550 |
| Haiku 4.5 | $0.00011 | $0.00275 |
Grade A, and why
hackathon-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 2mo 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hackathon Finder
Build a tech profile from everything known about you, then search Devpost, Luma, Partiful, MLH, and Eventbrite for upcoming hackathons — local or online — that match your stack and give you the best shot at winning.
Pre-flight Check (REQUIRED)
Before making any TinyFish call, always run BOTH checks:
1. CLI installed?
which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"
If not installed, stop and tell the user:
Install the TinyFish CLI:
npm install -g @tiny-fish/cli
2. Authenticated?
tinyfish auth status
If not authenticated, stop and tell the user:
You need a TinyFish API key. Get one at: https://agent.tinyfish.ai/api-keys
Then authenticate:
tinyfish auth login
Do NOT proceed until both checks pass.
Step 1 — Build the user's tech profile
Before searching for anything, build a picture of who you're helping. Draw from everything available in the current conversation and session context:
- Languages and frameworks mentioned or used (e.g. React, Python, Rust)
- Projects described or worked on
- Areas of interest expressed (e.g. AI/ML, Web3, hardware, design)
- Skill level signals (beginner, experienced, specialist)
- Any past hackathon experience mentioned
Summarize this as a brief internal profile:
Tech profile:
- Primary languages: {e.g. Python, TypeScript}
- Frameworks / tools: {e.g. React, FastAPI, LangChain}
- Interest areas: {e.g. AI, developer tools, consumer apps}
- Skill level: {beginner / intermediate / experienced}
- Past hackathons: {yes/no, any wins?}
If very little is known, ask one quick question:
"What do you usually build with? (e.g. languages, frameworks, or areas like AI, web, mobile)"
Step 2 — Ask for location and format preference
Ask the user two things before searching:
Two quick questions:
1. **Where are you based?** (city and country — e.g. "Singapore", "London, UK", "Austin, TX")
Or if you prefer online-only hackathons, just say "online".
2. **What are you optimizing for?**
- 🏆 Best chance of winning (match your stack to the theme)
- 🌍 Biggest / most prestigious (large prize pools, well-known sponsors)
- 🤝 Best for networking / meeting people
- 🧪 Most interesting theme (something you'd genuinely enjoy building)
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.
- 2mo ago First seen · 308 lines · 110 tokens per session scan A acaf3b0003cc
hackathon-finder is a skill published in the GitHub repository tinyfish-io/tinyfish-cookbook (2,313 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 2,752 once invoked, about $0.0004 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.
hackathon-finder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hackathon-findertinyfish-io/tinyfish-cookbook | Skill | 2.3k | 3d ago | MIT | A | 110 | Claude Code, Codex |
| typescript-strictBlackBeltTechnology/pi-agent-dashboard | Skill | 341 | today | MIT | A | 41 | Claude Code, Codex |
| podcast-generationbytedance/deer-flow | Skill | 85k | today | MIT | A | 38 | Claude Code, Codex |
| skill-reviewerbytedance/deer-flow | Skill | 85k | today | MIT | A | 38 | Claude Code |
| surprise-mebytedance/deer-flow | Skill | 85k | today | MIT | A | 67 | Claude Code, Codex |
| zeroclaw-docszeroclaw-labs/zeroclaw | Skill | 33k | today | Apache-2.0 | A | 80 | Claude Code, Codex |
| investigatevercel/eve | Skill | 5.8k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |