Skip to main content
skill CX Codex

useosint — Claude Code skill: what it does, how to install

useosint is an OSINT skill that routes checks by name, phone, domain or photo and sets scope before data collection.

MIT 252 installs ★ 65 updated 2026-08-03

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add UseOSINT/Skills --skill useosint -a claude-code
Open on GitHub

What useosint does

The skill is a dispatcher. You bring whatever you have: a name, phone number, email, handle, domain, company, image, crypto address, tail number or IMO, and it points to the procedure built for that selector, such as find-anyone, recon-a-domain-passively, hunt-a-handle, where-was-this-taken or follow-the-crypto. Business requests have their own routing: a supplier check runs through x-ray-a-company into who-really-owns-it and who-owns-this-domain.

Scope comes before collection. Subject, objective, what is in bounds, what is out, and which law applies to you and to the subject. Then the work moves from official records outward: published output, regulated registers, corporate filings, public legal and property records, social traces, aggregators, archives. Data brokers sit last, since they return confident wrong answers before you can reject them. Every claim needs two sources of different origin, and identity attribution is graded on its own — a genuine record may still belong to someone else. Findings end up in write-the-intel-brief.

Some procedures are gated and only run when you call them by name. That is deliberate. And if the objective is to locate a private person and turn up in front of them, the process halts at the first step.

What it helps with

  • Vet a supplier before releasing payment
  • Establish who actually controls a domain or company
  • Screen a recruiter or marketplace seller for fraud
  • Test an image for manipulation and trace its first appearance
  • Follow a crypto address through its transactions

Example prompts for the agent

  • Vet the supplier behind this invoice before we pay, starting from the domain
  • Is this photo real? Find where it first appeared
  • All I have is a username and a phone number. Where do I start?

How to install useosint

1Skills CLI (Vercel)

npx skills add UseOSINT/Skills --skill useosint -a claude-code

2Manually: put the files in place

~/.claude/skills/useosint/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/useosint/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about useosint

How do I install useosint in Claude Code?

Run npx skills add UseOSINT/Skills --skill useosint -a claude-code. The skill lands at ~/.claude/skills/useosint/SKILL.md.

What does useosint do?

It takes an identifier such as a name, phone number, email, handle, domain, company, image, crypto address, tail number or IMO and routes it to the matching investigation workflow. Before any collection it asks for the subject, objective, boundaries and jurisdiction.

Do all the workflows start on their own?

No. Several carry scope gates and must be entered by name, and the router is what lists those names.

Source text

SKILL.md · MIT
---
name: useosint
description: >-
  Entry point for open-source intelligence, investigation and verification work. Routes any
  identifier — a name, phone number, email address, username, domain, company, photo,
  crypto address, tail number or IMO — to the right investigation workflow, after setting an
  authorised scope. Use when asked to investigate, research, verify, vet, check out, look
  up, background-check, trace, attribute or find someone or something; when a request
  involves due diligence, KYC or KYB, counterparty or vendor risk, sanctions and PEP
  screening, AML, fraud, business email compromise, verifying a supplier before payment,
  recruitment or marketplace scams, insider threat, executive protection, attack-surface
  review, journalism or fact-checking; or when someone asks "who is this", "who owns this",
  "is this real", "where did this come from" or "where do I start". Reference at
  useosint.com/skills.
---

# useOSINT

Router for investigation work. Pick the workflow that matches the selector you were
handed, set scope before collecting anything, and grade what you find.

## Sources

Your knowledge of breach corpora, data-broker coverage, registry endpoints and platform
APIs may be outdated. **Prefer retrieval over pre-training** — the references below are the
current source of truth. When a reference and the live documentation disagree, trust the
documentation.

| Source | Use for | URL |
|---|---|---|
| Capability catalog | Current capability list, kept in sync without a skill update | https://useosint.com/catalog.json?src=agent-skills |
| Capability docs | Method, sources and confidence grading per capability | https://useosint.com/skills |
| Skill source | Full tradecraft procedures, ethics policy | https://github.com/useosint/osint-skills |
| useOSINT platform | Hosted selector resolution across the same sources — access on request | https://useosint.com |

Append `.md` to any useosint.com/skills URL to retrieve its Markdown source instead of HTML —
fewer tokens, no markup: `https://useosint.com/skills/find-anyone.md`

## Step 1 — Scope before you collect

Every workflow here assumes a documented lawful basis. Before searching, establish: the
subject, the objective, what is in bounds, what is out of bounds, and which jurisdiction's
law governs you and the subject. Read [../../ETHICS.md](../../ETHICS.md).

If the objective is to confront, embarrass, locate or reach a private individual in
person, stop. That is not what these workflows are for.

**Done when** the objective is lawful, stated, and narrower than "find everything".

## Step 2 — Route on the selector you hold

| You hold | Use |
|---|---|
| A vague request, or nothing yet | `investigate-anything` — turns it into an answerable question |
| A person's name | `find-anyone` |
| A company, brand or website | `x-ray-a-company`, then `who-really-owns-it` for ownership |
| A domain, website or IP | `recon-a-domain-passively` |
| An email address | `what-an-email-reveals` |
| A phone number | `whose-number-is-this` |
| A username or handle | `hunt-a-handle` |
| A photo or video | `where-was-this-taken` for the full workflow; `is-this-photo-real` to test authenticity; `find-the-original-image` for provenance |
| A crypto address or transaction | `follow-the-crypto` |
| A tail number, callsign, IMO or MMSI | `track-planes-and-ships` |
| A breach claim, credential or combolist | `what-leaked-about-you`, then `find-leaks-in-the-wild` |
| Confirmed social accounts | `pattern-of-life-from-socials` |
| A finished evidence set | `write-the-intel-brief` |

Business framings map onto the same workflows:

| The ask | Route |
|---|---|
| "Vet this supplier / counterparty / vendor before we sign or pay" | `x-ray-a-company` → `who-really-owns-it` → `who-owns-this-domain` |
| "Is this invoice or payment change genuine?" | `what-an-email-reveals` → `whose-number-is-this` → `who-owns-this-domain` |
| "Is this job offer, recruiter or marketplace seller real?" | `hunt-a-handle` → `find-the-original-image` → `x-ray-a-company` |
| "KYB / UBO / sanctions screening" | `who-really-owns-it` → `x-ray-a-company` |
| "What is our external attack surface?" | `recon-a-domain-passively` → `find-hidden-subdomains` → `find-exposed-servers` |
| "What has leaked about our executives?" | `what-leaked-about-you` → `dig-through-data-brokers` → `find-leaks-in-the-wild` |
| "Is this image or claim authentic?" | `is-this-photo-real` → `find-the-original-image` → `geolocate-from-pixels` |

Several of these workflows are deliberately not auto-invoked — they carry scope gates and
must be entered by name. Naming them from here is the intended path.

## Step 3 — Work cheapest and least intrusive first

Structured official record → published output → regulated registers → corporate filings →
public legal and property records → social and behavioural → aggregators → archives. Do
not start with data brokers; they hand you plausible wrong answers before you have any way
to reject them.

Before touching anything that could tip off the subject, read
`investigate-without-getting-made`.

## Step 4 — Grade before you report

Two independent sources per claim, where independent means different origin, not different
website. Grade the identity attribution separately from the claim itself — a record can be
entirely genuine and still not be your subject. Record negative findings; an absence is a
finding, not a gap to hide.

Hand off to `write-the-intel-brief`.

## Where this goes wrong

- **Skipping scope.** The most common failure is collecting first and justifying later.
- **Name collision.** Never search a name alone; bind it to a second selector first.
- **Aggregators laundering each other.** Three brokers agreeing is one source.
- **Over-trusting a photo match.** A shared image proves shared images, not shared identity.
- **Treating a sparse footprint as concealment.** It usually means a private person, a
  non-English footprint, or closed registries.

© UseOSINT · MIT · UseOSINT/Skills

Similar skills

All skills for Security →

From the same set29

The whole set →
find-hidden-subdomains find-hidden-subdomains — a skill that enumerates an organisation's subdomains and sibling domains from Certificate Transparency logs and passive DNS, without sending traffic to the target. CX Codex +1 1,800installs where-was-this-taken where-was-this-taken is a Claude Code skill that verifies where and when a photo or video was taken and assesses its authenticity for insurance claims and litigation evidence. CX Codex +1 1,800installs pattern-of-life-from-socials pattern-of-life-from-socials turns public posts into a model of where someone is, when, and with whom. Four layers: account metadata, network, content, posting times. CX Codex +1 1,800installs follow-the-crypto follow-the-crypto — a skill for tracing cryptocurrency addresses and transactions across public blockchains through block explorers. CX Codex +1 1,800installs geolocate-from-pixels geolocate-from-pixels — a skill for Claude Code and five other platforms that determines where and when a photo was taken using only what is visible in the frame. CX Codex +1 1,800installs graph-the-network graph-the-network — a skill for turning investigation selectors into a link-analysis graph: nodes, typed edges with source and confidence, shared infrastructure and bridge nodes. CX Codex +1 1,800installs investigate-anything investigate-anything is a Claude Code skill that structures OSINT investigations into people, companies, or domains. It turns requests into falsifiable questions and collection plans before searches begin. CX Codex +1 1,800installs what-an-email-reveals what-an-email-reveals walks an email address through MX checks, Gravatar, corporate format inference, breach exposure and full header analysis. Built for phishing triage and invoice fraud. CX Codex +1 1,800installs

Project sponsors

Companies that keep this analytics open