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 RudraDudhat2509/claude-skills --skill firecrawl-interactgit clone --depth 1 https://github.com/RudraDudhat2509/claude-skillsWrote 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/rudradudhat2509/claude-skills/firecrawl-interact)<a href="https://agentmods.dev/skills/rudradudhat2509/claude-skills/firecrawl-interact"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/firecrawl-interact/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/rudradudhat2509/claude-skills/firecrawl-interact"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/firecrawl-interact.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00160 | $0.00901 |
| Opus 5.5 | $0.00064 | $0.00360 |
| Sonnet 5.5 | $0.00032 | $0.00180 |
| Haiku 4.5 | $0.00016 | $0.00090 |
Grade A, and why
firecrawl-interact 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
firecrawl interact
Interact with scraped pages in a live browser session. Scrape a page first, then use natural language prompts or code to click, fill forms, navigate, and extract data.
When to use
- Content requires interaction: clicks, form fills, pagination, login
scrapefailed because content is behind JavaScript interaction- You need to navigate a multi-step flow
- Last resort in the workflow escalation pattern: search → scrape → map → crawl → interact
- Never use interact for web searches — use
searchinstead
Quick start
# 1. Scrape a page (scrape ID is saved automatically)
firecrawl scrape "<url>"
# 2. Interact with the page using natural language
firecrawl interact --prompt "Click the login button"
firecrawl interact --prompt "Fill in the email field with [email protected]"
firecrawl interact --prompt "Extract the pricing table"
# 3. Or use code for precise control
firecrawl interact --code "agent-browser click @e5" --language bash
firecrawl interact --code "agent-browser snapshot -i" --language bash
# 4. Stop the session when done
firecrawl interact stop
Options
| Option | Description |
|---|---|
--prompt <text> |
Natural language instruction (use this OR --code) |
--code <code> |
Code to execute in the browser session |
--language <lang> |
Language for code: bash, python, node |
--timeout <seconds> |
Execution timeout (default: 30, max: 300) |
--scrape-id <id> |
Target a specific scrape (default: last scrape) |
-o, --output <path> |
Output file path |
Profiles
Use --profile on the scrape to persist browser state (cookies, localStorage) across scrapes:
# Session 1: Login and save state
firecrawl scrape "https://app.example.com/login" --profile my-app
firecrawl interact --prompt "Fill in email with [email protected] and click login"
# Session 2: Come back authenticated
firecrawl scrape "https://app.example.com/dashboard" --profile my-app
firecrawl interact --prompt "Extract the dashboard data"
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 · 84 lines · 160 tokens per session scan A f6ddfc4b857a
firecrawl-interact is a skill published in the GitHub repository RudraDudhat2509/claude-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 160 tokens to every session and 901 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-browser
Drive Chrome with OpenCLI to inspect pages, interact with logged-in sites, capture API evidence, and manage native tabs, groups and windows. For reusable adapters, see opencli-adapter-author.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
url-to-code
Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.