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 themuuln/firecrawl-pool-proxy --skill firecrawl-poolgit clone --depth 1 https://github.com/themuuln/firecrawl-pool-proxyWrote 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/themuuln/firecrawl-pool-proxy/firecrawl-pool)<a href="https://agentmods.dev/skills/themuuln/firecrawl-pool-proxy/firecrawl-pool"><img src="https://agentmods.dev/badge/skills/themuuln/firecrawl-pool-proxy/firecrawl-pool/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/themuuln/firecrawl-pool-proxy/firecrawl-pool"><img src="https://agentmods.dev/badge/skills/themuuln/firecrawl-pool-proxy/firecrawl-pool.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 | $0.00000 | $0.00487 |
| Opus 5.5 | $0.00000 | $0.00195 |
| Sonnet 5.5 | $0.00000 | $0.00097 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
firecrawl-pool 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 2mo 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.
What it actually says
firecrawl-pool
Multi-key Firecrawl proxy. Pools multiple API keys, routes to the healthiest, retries on 402, falls back to free tier.
Quick Start
# 1. Install
pi install npm:firecrawl-pool
# 2. Setup (interactive wizard)
firecrawl-pool init
# 3. Verify
firecrawl-pool status
# 4. Add to your MCP config
# The pi extension handles this automatically
CLI Commands
| Command | What it does |
|---|---|
firecrawl-pool init |
Interactive setup wizard — creates keys file |
firecrawl-pool status |
Show key balances and health |
firecrawl-pool validate |
Test that all keys work |
firecrawl-pool proxy |
Run the MCP proxy (default) |
firecrawl-pool help |
Show help |
Keys File
Default location: ~/.config/firecrawl/keys.json
Or set FIRECRAWL_KEYS_FILE=/path/to/keys.json.
{
"version": 1,
"upstream": "https://api.firecrawl.dev",
"cooldown": { "baseMs": 900000, "maxMs": 21600000 },
"keys": [
{ "id": "personal", "apiKey": "fc-KEY-1", "enabled": true },
{ "id": "work", "apiKey": "fc-KEY-2", "enabled": true }
]
}
Features
- Credit-aware routing (probes balances, routes to healthiest key)
- 402 auto-retry across keys
- Keyless fallback for search/scrape when all keys die
- Cooldown with exponential backoff
- Go binary (~5MB RAM) or Node.js fallback
Auto-discovery
Looks for keys file in order:
FIRECRAWL_KEYS_FILEenv varfirecrawl-keys.jsonnext to the binary~/.config/firecrawl/keys.json~/.firecrawl-keys.json
Tools
All 24 Firecrawl tools: scrape, search, map, crawl, extract, interact, agent, monitors, research, etc.
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.
- 2mo ago First seen · 68 lines · 0 tokens per session scan A 918607c9b0b7
firecrawl-pool is a skill published in the GitHub repository themuuln/firecrawl-pool-proxy (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 487 tokens. 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.
firecrawl-pool compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| firecrawl-poolthemuuln/firecrawl-pool-proxy | Skill | 2 | 3mo ago | MIT | A | 0 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |