Firecrawl Web Agent is an open-source foundation for building AI agents that research the web with structured results. Developers can use its templates, agent core, web tools, and SDK to create applications that plan research tasks, interact with websites, and combine observations into answers. The catalogue entries are skills for this web-research agent.
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 firecrawl/web-agent --skill competitor-analysisgit clone --depth 1 https://github.com/firecrawl/web-agentWrote 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/firecrawl/web-agent/competitor-analysis)<a href="https://agentmods.dev/skills/firecrawl/web-agent/competitor-analysis"><img src="https://agentmods.dev/badge/skills/firecrawl/web-agent/competitor-analysis/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/firecrawl/web-agent/competitor-analysis"><img src="https://agentmods.dev/badge/skills/firecrawl/web-agent/competitor-analysis.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 | $0.00108 | $0.01083 |
| Opus 5.5 | $0.00043 | $0.00433 |
| Sonnet 5.5 | $0.00022 | $0.00217 |
| Haiku 4.5 | $0.00011 | $0.00108 |
Grade A, and why
competitor-analysis 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Analysis
Structured side-by-side comparison of competing products. Designed for search + scrape; no interact needed for typical marketing/pricing pages.
When to use
- User names 2+ companies or products: "compare Vercel, Netlify, Cloudflare Pages"
- User names a category only: "best CDNs for edge functions" — search to discover the top 3–5 players, then analyze
- User asks for alternatives: "what are the alternatives to X?"
- User wants a feature matrix or positioning summary
Do NOT use for single-vendor deep-dives — use deep-research or structured-extraction instead.
Strategy
-
Identify competitors.
- If the user listed them, use that list.
- Otherwise search once:
"top <category> providers 2026"or"<product> alternatives". Pick the 3–5 most-cited.
-
For each competitor, gather three pages:
- Homepage — one-line positioning, target audience
- Pricing page (usually
/pricingor/plans) — tiers, units, free tier, enterprise gate - Features or product page — top 5–10 capabilities, any standout differentiators
-
Fan out when scale warrants.
- 2–3 competitors: stay in the orchestrator, scrape serially or with parallel tool calls.
- 4+ competitors: use
spawnAgents, one worker per competitor. Each worker gets the 3 URLs above and returns a normalized sub-object.
-
Normalize before formatting.
- Align pricing tiers by role (Free / Pro / Team / Enterprise) even when vendors name them differently.
- Call out where a competitor has a capability the others don't.
- Flag anything missing (e.g. "Enterprise pricing is contact-sales only").
-
Call
formatOutputonce at the end with the full matrix.
Quick start
await agent.run({
prompt: 'Compare Vercel, Netlify, and Cloudflare Pages on pricing, edge functions, and free tier generosity',
skills: ['competitor-analysis'],
format: 'json',
})
// User gave only a category — discover competitors first
await agent.run({
prompt: 'Compare the top 4 vector databases for production RAG workloads',
skills: ['competitor-analysis'],
format: 'json',
})
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 · 107 lines · 108 tokens per session scan A f74300e388c3
competitor-analysis is a skill published in the GitHub repository firecrawl/web-agent (1,248 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 1,083 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.