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 tenders-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/tenders-finder)<a href="https://agentmods.dev/skills/tinyfish-io/tinyfish-cookbook/tenders-finder"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/tenders-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/tenders-finder"><img src="https://agentmods.dev/badge/skills/tinyfish-io/tinyfish-cookbook/tenders-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 | $0.00139 | $0.02418 |
| Opus 5 | $0.00069 | $0.01209 |
| Sonnet 5 | $0.00028 | $0.00484 |
| Haiku 4.5 | $0.00014 | $0.00242 |
Grade A, and why
tenders-finder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Singapore Government Tender Finder
Given a sector, scrape live Singapore government tender portals in parallel using TinyFish agents — returning only open tenders with upcoming submission deadlines.
Pre-flight check
tinyfish --version
tinyfish auth status
If not installed: npm install -g tinyfish
If not authenticated: tinyfish auth login
Step 1 — Clarify inputs
You need:
- Sector — one of:
IT / Software,Construction,Healthcare,Consulting,Logistics,Education
If not specified, ask before proceeding. If the user gives a related term (e.g. "tech", "software"), map it to the closest sector.
Get today's date — you will use it to filter out tenders whose deadline has already passed.
Step 2 — Parallel scraping
Fire all 5 agents simultaneously against the fixed portal list used by the app.
TODAY=$(date '+%A, %B %d, %Y')
# Agent 1 — GeBIZ (official Singapore government portal)
tinyfish agent run \
--url "https://www.gebiz.gov.sg/" \
"You are on GeBIZ, Singapore's official government procurement portal. Today is ${TODAY}.
TASK: Extract open government tenders for the sector: {SECTOR}.
Scroll through the page to find tender listings.
For each tender extract:
- Tender Title
- Tender ID (official reference number)
- Issuing Authority (government agency)
- Country / Region: Singapore
- Tender Type (Open / Selective / Limited)
- Publication Date
- Submission Deadline
- Tender Status (Open / Closed)
- Official Tender URL (direct link)
- Brief Description (short summary)
- Eligibility Criteria (requirements if shown)
- Industry / Category: {SECTOR}
STRICT RULES:
- Only return tenders with Submission Deadline AFTER today (${TODAY}) — skip expired ones
- Only return tenders relevant to {SECTOR} — skip unrelated ones
- Do NOT click individual tender links unless the listing has no detail visible
- Do NOT paginate
- Scroll maximum twice then stop
- Maximum 5 tenders then stop immediately
Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
\"Country / Region\", \"Tender Type\", \"Publication Date\", \"Submission Deadline\",
\"Tender Status\", \"Official Tender URL\", \"Brief Description\",
\"Eligibility Criteria\", \"Industry / Category\"}]}" \
--sync --browser-profile stealth > /tmp/tf_gebiz.json &
# Agent 2 — Tenders On Time
tinyfish agent run \
--url "https://www.tendersontime.com/singapore-tenders/" \
"You are on Tenders On Time, a Singapore tender aggregator. Today is ${TODAY}.
TASK: Extract open tenders for the sector: {SECTOR}.
Read the visible tender listings on this page.
For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
STRICT RULES:
- Only return tenders with Submission Deadline AFTER today — skip expired ones
- Only return tenders relevant to {SECTOR}
- Do NOT click any tender link
- Do NOT scroll more than twice
- Do NOT paginate
- Maximum 5 tenders then stop
Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
\"Publication Date\", \"Submission Deadline\", \"Tender Status\",
\"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
--sync > /tmp/tf_tendersontime.json &
# Agent 3 — Bid Detail
tinyfish agent run \
--url "https://www.biddetail.com/singapore-tenders" \
"You are on Bid Detail, a tender listing site. Today is ${TODAY}.
TASK: Extract open Singapore tenders for the sector: {SECTOR}.
Read the visible tender listings on this page.
For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
STRICT RULES:
- Only return tenders with Submission Deadline AFTER today — skip expired ones
- Only return tenders relevant to {SECTOR}
- Do NOT click any tender link
- Do NOT scroll more than twice
- Do NOT paginate
- Maximum 5 tenders then stop
Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
\"Publication Date\", \"Submission Deadline\", \"Tender Status\",
\"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
--sync > /tmp/tf_biddetail.json &
# Agent 4 — Tenders Info
tinyfish agent run \
--url "https://www.tendersinfo.com/global-singapore-tenders.php" \
"You are on Tenders Info, a global tender database. Today is ${TODAY}.
TASK: Extract open Singapore tenders for the sector: {SECTOR}.
Read the visible tender listings on this page.
For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
STRICT RULES:
- Only return tenders with Submission Deadline AFTER today — skip expired ones
- Only return tenders relevant to {SECTOR}
- Do NOT click any tender link
- Do NOT scroll more than twice
- Do NOT paginate
- Maximum 5 tenders then stop
Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
\"Publication Date\", \"Submission Deadline\", \"Tender Status\",
\"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
--sync > /tmp/tf_tendersinfo.json &
# Agent 5 — Global Tenders
tinyfish agent run \
--url "https://www.globaltenders.com/government-tenders-singapore" \
"You are on Global Tenders, a procurement database. Today is ${TODAY}.
TASK: Extract open Singapore tenders for the sector: {SECTOR}.
Read the visible tender listings on this page.
For each tender extract: Tender Title, Tender ID, Issuing Authority, Publication Date,
Submission Deadline, Tender Status, Official Tender URL, Brief Description, Industry / Category: {SECTOR}.
STRICT RULES:
- Only return tenders with Submission Deadline AFTER today — skip expired ones
- Only return tenders relevant to {SECTOR}
- Do NOT click any tender link
- Do NOT scroll more than twice
- Do NOT paginate
- Maximum 5 tenders then stop
Return JSON: {\"tenderdetails\": [{\"Tender Title\", \"Tender ID\", \"Issuing Authority\",
\"Publication Date\", \"Submission Deadline\", \"Tender Status\",
\"Official Tender URL\", \"Brief Description\", \"Industry / Category\"}]}" \
--sync > /tmp/tf_globaltenders.json &
# Wait for all agents
wait
echo "=== GEBIZ ===" && cat /tmp/tf_gebiz.json
echo "=== TENDERSONTIME ===" && cat /tmp/tf_tendersontime.json
echo "=== BIDDETAIL ===" && cat /tmp/tf_biddetail.json
echo "=== TENDERSINFO ===" && cat /tmp/tf_tendersinfo.json
echo "=== GLOBALTENDERS ===" && cat /tmp/tf_globaltenders.json
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.
- 10d ago First seen · 244 lines · 139 tokens per session scan A 65551eff2764
tenders-finder is a skill published in the GitHub repository tinyfish-io/tinyfish-cookbook (2,156 stars, last pushed 9d ago), licensed MIT. It adds 139 tokens to every session and 2,418 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
11-browser-qa
Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron desktop apps — navigating, filling forms, clicking, screenshots, extracting data, testing web apps, visual UI checks, the Pi Dashboard's Electron shell, or the user's own logged-in browser (SSO/2FA sites). Triggers…
06-test
Write and iterate tests until they pass, or validate a user journey end to end in the browser. Use when the user wants to add coverage, find what's untested, or walk a flow. Not for auditing test health or debugging a failure.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
web-game-development
Implement and optimize browser games using Phaser, Three.js, React Three Fiber, Babylon.js, or PlayCanvas with responsive input, asset loading, rendering, and browser playtests. Use for JavaScript or TypeScript game projects.
browser-qa
Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.