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 feedbackgit 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/feedback)<a href="https://agentmods.dev/skills/tinyfish-io/tinyfish-cookbook/feedback"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/feedback/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/feedback"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 15 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00054 | $0.00579 |
| Opus 5.5 | $0.00022 | $0.00232 |
| Sonnet 5.5 | $0.00011 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
feedback 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TinyFish Feedback
Collect the user's feedback, structure it, preview it, then file it. Nothing leaves the machine without the user seeing the exact text first.
Collect
Ask (briefly) for: what they were trying to do, what happened instead, and
what they expected. For anything setup-, auth-, or connectivity-shaped, run
npx -y @tiny-fish/cli@latest doctor and offer to attach its stdout JSON
verbatim — it is schema-versioned and already redaction-safe (undeclared
fields stripped on parse, messages authored rather than raw). Do not add
fields, summarise it, or paste config contents alongside it. On exit 2
doctor produced no JSON — say so instead of attaching an empty report.
Structure
### What I was doing
…
### What happened
…
### Expected
…
### Environment
harness + version, CLI version (if known)
### Doctor report (optional)
`tinyfish doctor` stdout, verbatim
Preview gate
Show the complete issue body to the user and ask for an explicit yes before filing. Any edit they request happens before filing.
File
- Preferred: write the body and the title to files, then
gh issue create --repo tinyfish-io/tinyfish-cookbook --title "$(cat "$title_file")" --body-file "$body_file"(only ifghis installed and authenticated). Both values come from the user's free-form text (the body also carries doctor's JSON), so neither may reach the shell as literal text — including in atitle=…assignment, where backticks or$(…)are evaluated just the same.cat's output is not re-parsed. Never build the command as a string or run it througheval. - Fallback: open a prefilled issue URL
(
https://github.com/tinyfish-io/tinyfish-cookbook/issues/new?title=…&body=…). Percent-encode both values — an unencoded#truncates the body and&splits it into junk parameters. URL length limits truncate long bodies anyway — if the body was truncated, tell the user and show the full text so they can paste the remainder.
This repo is public — remind the user of that in the preview if the report contains anything they typed free-form.
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.
- 1mo ago First seen · 60 lines · 54 tokens per session scan A 1047dd9c59c2
feedback is a skill published in the GitHub repository tinyfish-io/tinyfish-cookbook (2,263 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 579 once invoked, about $0.0002 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.
Other skills, from other repositories
investigate
Investigate a specific issue report with strict, evidence-driven diagnosis.
code-search
Search a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.
ci-troubleshoot
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and retrigger jobs. Use when a CI run is red, a release is stuck, a workflow won't dispatch, or you need to know which workflow does…
performance-optimization
Measure-first performance work. Use on triggers like "it's slow", "profile this", "optimize perf", "fix the bottleneck", "improve load time / Core Web Vitals", or when a measured regression needs fixing. Enforces measure-before-optimize. Fills a perf gap not covered by existing project skills. Not a build/ship…
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…
debug-dashboard
Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries. Routes UI/visual issues to the browser skill. Use when the server seems hung, a pi session won't connect, tests fail mysteriously, the dashboard shows a blank…