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 yonatangross/orchestkit --skill web-research-workflowgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/web-research-workflow)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/web-research-workflow"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/web-research-workflow.svg" alt="Measured on agentmods" 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 Excessive Agency · line 17 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00072 | $0.00989 |
| Opus 5 | $0.00036 | $0.00495 |
| Sonnet 5 | $0.00014 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
web-research-workflow 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 yesterday.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research Workflow
Unified approach for web content research that automatically selects the right tool for each situation.
Quick Decision Tree
URL to research
│
▼
┌─────────────────┐
│ 1. Try WebFetch │ ← Fast, free, no overhead
│ (always try) │
└─────────────────┘
│
Content OK? ──Yes──► Parse and return
│
No (empty/partial/<500 chars)
│
▼
┌───────────────────────┐
│ 2. TAVILY_API_KEY set?│
└───────────────────────┘
│ │
Yes No ──► Skip to step 3
│
▼
┌───────────────────────────┐
│ Tavily search/extract/ │ ← Raw markdown, batch URLs
│ crawl/research │
└───────────────────────────┘
│
Content OK? ──Yes──► Parse and return
│
No (JS-rendered/auth-required)
│
▼
┌─────────────────────┐
│ 3. Use agent-browser │ ← Full browser, last resort
└─────────────────────┘
│
├─ SPA (react/vue/angular) ──► wait --load networkidle
├─ Login required ──► auth flow + state save
├─ Dynamic content ──► wait --text "Expected"
└─ Multi-page ──► crawl pattern
Tavily Enhanced Research
When TAVILY_API_KEY is set, Tavily provides a powerful middle tier between WebFetch and agent-browser. It returns raw markdown content, supports batch URL extraction, and offers semantic search with relevance scoring. If TAVILY_API_KEY is not set, the 3-tier tree collapses to 2-tier (WebFetch → agent-browser) automatically.
Load details: Read("rules/tool-selection.md") for when-to-use-what tables, escalation heuristics, SPA detection patterns, and cost awareness.
Load details: Read("references/tavily-api.md") for Search, Extract, Map, Crawl, and Research endpoint examples and options.
Browser Patterns
For content requiring JavaScript rendering, authentication, or multi-page crawling, fall back to agent-browser.
Load details: Read("rules/browser-patterns.md") for auto-fallback, authentication flow, multi-page research patterns, best practices, and troubleshooting.
What ships with it
8 files 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.
- yesterday Changed 8676f539cec3
- 3d ago First seen · 116 lines · 72 tokens per session scan A 56bbfc64fcd6
web-research-workflow is a skill published in the GitHub repository yonatangross/orchestkit (231 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 989 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
Browser Use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
browser-automation
Browser automation with Playwright — testing, scraping, monitoring, form submission, screenshot capture, and multi-page interaction flows. Covers setup, navigation, element interaction, assertions, and cleanup. Primary keyword clusters: Playwright browser automation, end-to-end testing with Playwright, web scraping…
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
web-browse
Drive a headless browser to navigate pages, read content, click, and fill forms — for sites that need JavaScript rendering or interaction beyond a plain HTTP fetch.
fsb
FSB drives the user's Chrome via the FSB extension and an MCP bridge for live web tasks.
browser-qa-report
Runs a read-only browser QA pass and returns evidence.