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 Liberty91LTD/cti-skills --skill url-investigationgit clone --depth 1 https://github.com/Liberty91LTD/cti-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/liberty91ltd/cti-skills/url-investigation)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/url-investigation"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/url-investigation/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/liberty91ltd/cti-skills/url-investigation"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/url-investigation.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 | $0.00080 | $0.01775 |
| Opus 5 | $0.00040 | $0.00888 |
| Sonnet 5 | $0.00016 | $0.00355 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
url-investigation 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 9d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
url-investigation
Investigate a URL end-to-end. Scan it live (URLScan), cross-reference reputation (VT, OTX), extract parent domain + resolved IP for sibling investigations.
This skill invokes: /lookup-liberty91 (first-party — run first), /lookup-urlscan, /lookup-virustotal, /lookup-otx, optionally /lookup-reversinglabs (network threat-intel from RL malware corpus), optionally /lookup-crowdstrike (IOC reputation + actor/malware links), optionally /lookup-misp and/or /lookup-opencti (internal correlation), optionally /lookup-sentinel (exposure check in your own telemetry), optionally /domain-investigation and/or /ip-investigation for the parent/resolved infrastructure, then /source-assessment, /tlp-guide, /confidence-levels.
When to invoke
- User asks to scan, check, or investigate a URL
- User pastes a suspicious link from a phishing email
/domain-investigationor another skill hands off a specific URL for live-scan evidence
Inputs
indicator: <URL>
context: <optional — phishing email? user report? hunt result?>
tlp_ceiling: <optional, default AMBER — phishing-kit URLs often warrant AMBER+STRICT>
visibility: <unlisted | public — default unlisted for operational safety>
Procedure
1. Validate
- Confirm it's a valid URL (scheme + host minimum)
- Extract parent domain — useful for later pivots
- Extract path + query params (but DON'T include in URL if it contains credentials or user-identifying tokens)
2. Primary scan
/lookup-urlscan url <value> --visibility unlisted
This takes 45-90 seconds on first submission. While waiting, run the other lookups in parallel.
Visibility default is unlisted — public submissions expose the IOC on URLScan's global feed and can tip off threat actors. Only use public if the user explicitly requests it or the URL is already publicly known.
3. Parallel reputation lookups
/lookup-virustotal url <value> # aggregate reputation
/lookup-otx url <value> # community pulses referencing this URL
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.
- 9d ago First seen · 166 lines · 80 tokens per session scan A 9a38e58a71c1
url-investigation is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,775 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 2026-09-03.
Other skills, from other repositories
ai-browser-use
A business-diagnosis assistant for marketing, operations, product, and sales questions about how to approach a task.
test-engineer
Automated E2E testing with Playwright including the auto-fix loop — generate test cases from the UI, run them, fix failures and re-run until passing, then produce a human-readable report. Test until it passes, not just test and report. Drives /toh-test; use whenever tests must be written, run, or made green.
hatch3r-browser-verify
Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…
browser-qa
Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.
browser
Drive the user's REAL authenticated browser (their logins/cookies) via the local-browser chain — guilde → tunnel → daemon → chrome-devtools-mcp → cloned Chrome. The foundation skill for any "do X in a browser as me" task: navigate, capture (element screenshots + selective content/ld+json/readability), inspect network…
Drive the user's real authenticated LinkedIn — via camofox stealth (preferred, distinct session + WhatsApp re-auth alert) or the chrome-devtools chain (fallback). API-first: read feed/profiles/activity, who-reacted/commented, connections, people + content search (who posted about a topic, with resolved permalinks)…