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 npm-package-comparatorgit 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/npm-package-comparator)<a href="https://agentmods.dev/skills/tinyfish-io/tinyfish-cookbook/npm-package-comparator"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/npm-package-comparator.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.02094 |
| Opus 5 | $0.00056 | $0.01047 |
| Sonnet 5 | $0.00023 | $0.00419 |
| Haiku 4.5 | $0.00011 | $0.00209 |
Grade A, and why
npm-package-comparator 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 7d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
npm Package Comparator
Compare any set of npm packages side by side using live data from npm, GitHub, Bundlephobia, and Snyk — then give a clear recommendation based on what you actually need.
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 — Gather inputs
You need:
- Package names — 2 to 4 packages to compare (e.g.
zustand,jotai,redux) - Use case (optional but improves recommendation) — e.g. "small React app", "large enterprise codebase", "need SSR support"
If the user hasn't specified a use case, ask:
"What are you building with it? (e.g. small side project, large team codebase, performance-critical app)"
If they don't know, proceed without it and give a general recommendation.
Step 2 — Parallel data fetch
For each package, fire agents across npm, GitHub, Bundlephobia, and Snyk simultaneously. Run ALL agents for ALL packages in parallel — one agent per package per source.
# ── For each PACKAGE, run all 4 agents in parallel ───────────
# npm stats
tinyfish agent run \
--url "https://www.npmjs.com/package/{PACKAGE}" \
"You are on the npm page for the package {PACKAGE}.
Extract:
- current version
- weekly downloads (exact number shown)
- total downloads if shown
- last publish date
- license
- number of dependencies
- TypeScript support (yes/no — check if types are listed)
- maintainers count
- repository URL
STRICT RULES:
- Do NOT click any links
- Read only what is visible on this page
- If a field is not shown, return null
Return JSON: {package, version, weekly_downloads, last_published, license, dependency_count, typescript_support, maintainer_count, repo_url}" \
--sync > /tmp/npm_{PACKAGE_SAFE}.json &
# GitHub stats
tinyfish agent run \
--url "https://github.com/{OWNER}/{REPO}" \
"You are on the GitHub repository page for {PACKAGE}.
Extract:
- star count
- fork count
- open issues count
- last commit date
- number of contributors (from sidebar or Insights)
- latest release tag and date
- whether the repo is actively maintained (check: last commit within 6 months)
STRICT RULES:
- Do NOT click any tabs or links
- Read only what is visible on the main repo page
Return JSON: {package, stars, forks, open_issues, last_commit, contributors, latest_release, latest_release_date, is_active}" \
--sync > /tmp/gh_{PACKAGE_SAFE}.json &
# Bundle size
tinyfish agent run \
--url "https://bundlephobia.com/package/{PACKAGE}" \
"You are on the Bundlephobia page for {PACKAGE}.
Extract:
- minified size (in KB)
- minified + gzipped size (in KB)
- download time on slow 3G (if shown)
- tree-shakeable (yes/no)
- side-effect free (yes/no)
STRICT RULES:
- Do NOT click any links
- Read only what is visible on this page
- If the page hasn't loaded sizes yet, note it
Return JSON: {package, minified_kb, gzipped_kb, tree_shakeable, side_effect_free}" \
--sync > /tmp/bp_{PACKAGE_SAFE}.json &
# Known vulnerabilities
tinyfish agent run \
--url "https://security.snyk.io/package/npm/{PACKAGE}" \
"You are on the Snyk security page for the npm package {PACKAGE}.
Extract:
- total number of known vulnerabilities
- number by severity: critical, high, medium, low
- most recent vulnerability title and date (if shown)
STRICT RULES:
- Do NOT click any vulnerability links
- Read only the summary visible on this page
- If the page shows 'no vulnerabilities', return {total: 0}
Return JSON: {package, total_vulns, critical, high, medium, low, latest_vuln_title, latest_vuln_date}" \
--sync > /tmp/snyk_{PACKAGE_SAFE}.json &
# Repeat the above 4 agents for each additional package
# All backgrounded with & — fire everything at once then:
wait
# Collect all results
for p in {PACKAGE_LIST}; do
echo "=== $p ==="
cat /tmp/npm_${p}.json
cat /tmp/gh_${p}.json
cat /tmp/bp_${p}.json
cat /tmp/snyk_${p}.json
done
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.
- 7d ago First seen · 233 lines · 113 tokens per session scan A 805bb0c58ac6
npm-package-comparator is a skill published in the GitHub repository tinyfish-io/tinyfish-cookbook (2,153 stars, last pushed 6d ago), licensed MIT. It adds 113 tokens to every session and 2,094 once invoked, about $0.0006 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
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
theme-system
CSS custom properties theme architecture for 4 themes (studio, earth, athlete, gradient) with data-theme attribute switching and theme-aware components. Use when implementing theme switching, defining color schemes, or creating theme-responsive UI elements.
dashboard-plugin-scaffold
Scaffold a new pi-dashboard plugin in the dashboard monorepo, OR augment an existing pi-extension project on disk with dashboard plugin contributions. Hybrid skill: a single askuser batch up front, then prescriptive steps the agent follows. Use when the user asks to "create a dashboard plugin", "add dashboard support…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
component-architecture
Reusable component patterns for cards, sections, forms, and layouts with consistent prop interfaces and composition strategies. Use when creating new components, refactoring existing ones, or establishing component design patterns.