mcpField
O
OSINT

OSINT

github.com/danielmiesslerProductivity19.6k428 installsUpdated 1d ago
Repository

About OSINT

OSINT is a skill for authorized open-source investigations by researchers and analysts. It routes people, company, domain, organization, and threat inquiries to workflows, with authorization checks and ethical limits built in.

Key features

  1. 01Routes investigations by target type
  2. 02Checks authorization and scope first
  3. 03Catalogs public OSINT sources
  4. 04Uses research and reconnaissance skills
  5. 05Organizes active and archived reports

Use cases

  1. 01Research a person or company
  2. 02Assess a company for due diligence
  3. 03Investigate a domain or threat entity
  4. 04Research an NGO or government organization

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/danielmiessler/lifeos --skill osint

After installing, type/osintin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

CompanyTools.md
SOURCES.JSON
PeopleTools.md
EntityTools.md
SOURCES.md
EthicalFramework.md
Methodology.md
Workflows/
CompanyLookup.md
DomainLookup.md
DiscoverOSINTSources.md
CompanyDueDiligence.md
PeopleLookup.md
OrganizationLookup.md
EntityLookup.md

Details

From the project README

Customization

Before executing, check for user customizations at: ~/.claude/PAI/USER/SKILLCUSTOMIZATIONS/OSINT/

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

You MUST send this notification BEFORE doing anything else when this skill is invoked.

  1. Send voice notification:

    curl -s -X POST http://localhost:8888/notify \
  -H "Content-Type: application/json" \
  -d '{"message": "Running the WORKFLOWNAME workflow in the OSINT skill to ACTION"}' \
  > /dev/null 2>&1 &

  2. Output text notification:

    Running the **WorkflowName** workflow in the **OSINT** skill to ACTION...

This is not optional. Execute this curl command immediately upon skill invocation.

OSINT Skill

Open Source Intelligence gathering for authorized investigations.

Workflow Routing

Investigation TypeWorkflowContext
People lookupWorkflows/PeopleLookup.mdSOURCES.JSON
Company lookupWorkflows/CompanyLookup.mdSOURCES.JSON
Investment due diligenceWorkflows/CompanyDueDiligence.mdSOURCES.JSON
Entity/threat intelWorkflows/EntityLookup.mdSOURCES.JSON
Domain/subdomain investigationWorkflows/DomainLookup.mdSOURCES.JSON
Organization/NGO/gov researchWorkflows/OrganizationLookup.mdSOURCES.JSON
Discover new OSINT sourcesWorkflows/DiscoverOSINTSources.mdSOURCES.JSON

Trigger Patterns

People OSINT:

  • "do OSINT on [person]", "research [person]", "background check on [person]"
  • "who is [person]", "find info about [person]", "investigate this person" -> Route to Workflows/PeopleLookup.md

Company OSINT:

  • "do OSINT on [company]", "research [company]", "company intelligence"
  • "what can you find about [company]", "investigate [company]" -> Route to Workflows/CompanyLookup.md

Investment Due Diligence:

  • "due diligence on [company]", "vet [company]", "is [company] legitimate"
  • "assess [company]", "should we work with [company]" -> Route to Workflows/CompanyDueDiligence.md

Entity/Threat Intel:

  • "investigate [entity]", "threat intelligence on [entity]", "is this malicious"
  • "research this threat actor", "analyze [entity]", "check this IP" -> Route to Workflows/EntityLookup.md

Domain/Subdomain Investigation:

  • "investigate domain", "check domain", "subdomain enumeration"
  • "domain recon on [domain]", "what subdomains does [domain] have"
  • "DNS investigation", "certificate transparency for [domain]" -> Route to Workflows/DomainLookup.md

Organization/NGO/Government:

  • "research organization", "investigate NGO", "research agency"
  • "who is [organization]", "investigate [nonprofit]", "research [government agency]"
  • "what do we know about [association]", "background on [institution]" -> Route to Workflows/OrganizationLookup.md

Authorization (REQUIRED)

Before ANY investigation, verify:

  • Explicit authorization from client
  • Clear scope definition
  • Legal compliance confirmed
  • Documentation in place

STOP if any checkbox is unchecked. See EthicalFramework.md for details.

Resource Index

FilePurpose
SOURCES.JSONMaster catalog of 279 OSINT sources across 8 categories
SOURCES.mdHuman-readable source reference with descriptions and access info
EthicalFramework.mdAuthorization, legal, ethical boundaries
Methodology.mdCollection methods, verification, reporting
PeopleTools.mdPeople search, social media, public records (legacy — use SOURCES.JSON)
CompanyTools.mdBusiness databases, DNS, tech profiling (legacy — use SOURCES.JSON)
EntityTools.mdThreat intel, scanning, malware analysis (legacy — use SOURCES.JSON)

Integration

Automatic skill invocations:

  • Research Skill - Parallel researcher agent deployment (REQUIRED)
  • Recon Skill - Technical infrastructure reconnaissance

Agent fleet patterns:

  • Quick lookup: 4-6 agents
  • Standard investigation: 8-16 agents
  • Comprehensive due diligence: 24-32 agents

Researcher types:

ResearcherBest For
PerplexityResearcherCurrent web data, social media, company updates
ClaudeResearcherAcademic depth, professional backgrounds
GeminiResearcherMulti-perspective, cross-domain connections
GrokResearcherContrarian analysis, fact-checking

File Organization

Active investigations:

~/.claude/MEMORY/WORK/$(jq -r '.work_dir' ~/.claude/MEMORY/STATE/current-work.json)/YYYY-MM-DD-HHMMSS_osint-[target]/

Archived reports:

~/.claude/History/research/YYYY-MM/[target]-osint/

Ethical Guardrails

ALLOWED: Public sources only - websites, social media, public records, search engines, archived content

PROHIBITED: Private data, unauthorized access, social engineering, purchasing breached data, ToS violations

See EthicalFramework.md for complete requirements.

Version: 3.0 (SOURCES.JSON Integration) Last Updated: February 2026

Comments

Markdown supported