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 outscraper/outscraper-mcp-server --skill async-company-researchgit clone --depth 1 https://github.com/outscraper/outscraper-mcp-serverWrote 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/outscraper/outscraper-mcp-server/async-company-research)<a href="https://agentmods.dev/skills/outscraper/outscraper-mcp-server/async-company-research"><img src="https://agentmods.dev/badge/skills/outscraper/outscraper-mcp-server/async-company-research/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/outscraper/outscraper-mcp-server/async-company-research"><img src="https://agentmods.dev/badge/skills/outscraper/outscraper-mcp-server/async-company-research.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 | $0.00065 | $0.00379 |
| Opus 5 | $0.00032 | $0.00189 |
| Sonnet 5 | $0.00013 | $0.00076 |
| Haiku 4.5 | $0.00006 | $0.00038 |
Grade A, and why
async-company-research 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.
What it actually says
Async Company Research
Use this skill when the upstream task may not finish immediately and the workflow should explicitly handle request ids.
Workflow
- Choose the target tool.
- Submit with
execution_mode: "async". - Capture the returned
request_id. - Poll with
requests_get. - Once complete, summarize the final payload.
Tools This Skill Pairs Well With
company_insightsemails_and_contactsgoogle_maps_searchai_scraper
Canonical Pattern
Step 1. Submit
Example with company_insights:
{
"query": ["outscraper.com", "stripe.com", "notion.so"],
"fields": ["name", "description", "industry", "employees"],
"execution_mode": "async"
}
Step 2. Poll
Use requests_get:
{
"request_id": "REQUEST_ID_FROM_STEP_1"
}
Repeat until the job is complete or fails.
Behavior Rules
- Tell the user when an async job has been submitted.
- Do not pretend a pending request is complete.
- If the tool returns a completed response directly, summarize it immediately.
- If the job is still pending, say so clearly and give the request id.
Output Style
When complete, produce:
- the key result
- the business interpretation
- any missing or partial data that the user should know about
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 · 65 lines · 65 tokens per session scan A 5609a79b6a16
async-company-research is a skill published in the GitHub repository outscraper/outscraper-mcp-server (3 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 379 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
influencer-discovery
Find the bloggers/creators who can help promote your work, capture their contact info, and append them to the target sheet in Google Sheets. Targets must bring their own audience — followers, readers, subscribers; people building their own product are not targets. Use for requests like "find a batch of bloggers doing…
smb-sales-boost
Query and manage leads from the SMB Sales Boost B2B lead database. Search newly registered businesses, filter by location/industry/keywords, export leads, manage filter presets, and use AI-powered category suggestions. Requires SMBSALESBOOSTAPIKEY env var (smbk... prefix). Exports contain PII (phone numbers, emails).…
accounting-firm-lead-scraper
Collect accounting firm leads from Google Maps — business name, address, phone, website, rating. Use when the user wants to prospect local accounting firms or build a B2B contact list.
ad-landing-page-intent-monitor
Monitor ad landing pages for intent signals — offer type, CTA, contact form, email, company name. Use when the user wants to identify buyer intent from ad campaigns.
alignable-business-lead-scraper
name: alignable-business-lead-scraper description: "Collect Alignable business profiles — company, owner, location, category, website. Use when the user wants small-business networking leads." license: MIT metadata: author: rebeccareyes3794 version: "0.1.0".
angies-list-contractor-lead-scraper
name: angies-list-contractor-lead-scraper description: "Collect Angi contractor profiles — business, service, location, rating, reviews, phone. Use when the user wants home services leads." license: MIT metadata: author: rebeccareyes3794 version: "0.1.0".