claude-osint

2 paired Claude skills · 90+ recon modules · 48 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · 4,600+ lines of structured tradecraft. Drop-in SKILL.md files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.

Built by ElementalSoul — GenAI Security Research.

_{SPONSORED BY}

What is this?

claude-osint is a paired set of skills for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for one half of the offensive recon problem:

• osint-methodology - how to think. Strategic + procedural. Asset-graph discipline, severity rubric, time budgeting, identity-fabric mapping, deliverable templates.
• offensive-osint - what to reach for. Tactical arsenal. Probe paths, regexes, payloads, scoring rules, curl one-liners, tool URLs.

Drop both into your Claude environment and it behaves like a senior recon analyst: it knows the techniques, the tooling, the edge cases, and the escalation paths — and it stays in scope.

~4,600 lines of structured tradecraft · 96.9% PASS on a 32-prompt self-evaluation · ~85–90% practitioner coverage for the recon phase of authorized engagements.

Structure

claude-osint/
├── skills/
│   ├── osint-methodology/SKILL.md     # how to think  (455 lines)
│   └── offensive-osint/
│       ├── SKILL.md                   # what to reach for (4,168 lines)
│       ├── scripts/secret_scan.py     # stdlib-only secret scanner
│       └── scripts/h1_reference.py    # HackerOne disclosed-reports reference agent
├── docs/                              # architecture · coverage · install · usage
├── examples/                          # 4 end-to-end engagement walk-throughs
├── tests/smoke-test-prompts.md        # 32-prompt self-evaluation
└── assets/banner.png

Each skill directory is self-contained. Drop into ~/.claude/skills/ and Claude auto-triggers on relevant phrases.

Skill Index

90+ capabilities across 12 domains. Categorized like Claude-Red — pick a domain to drill in.

Reconnaissance & Asset Discovery

Identity & SSO Mapping

Web Application Attack Surface

Cloud & Container

Secret & Credential Hunting

Breach Intelligence

Vendor & Edge-Appliance Fingerprinting

Email Security

Human Intelligence

Supply Chain

Reporting & Deliverables

Sector-Specific

Capability Map

Two skills, twelve capability domains. Drill into the Skill Index above for concrete sub-capabilities.

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#1e293b','primaryTextColor':'#f1f5f9','primaryBorderColor':'#475569','lineColor':'#94a3b8'}}}%%
flowchart LR
    Root(["🦅 claude-osint"])

    Root --> M["📘 osint-methodology<br/><i>how to think</i>"]
    Root --> A["🛠️ offensive-osint<br/><i>what to reach for</i>"]

    M --> M1[Recon Pipeline]
    M --> M2[Asset Graph]
    M --> M3[Identity Fabric]
    M --> M4[Findings Rubric]
    M --> M5[Reporting Templates]
    M --> M6[OpSec & Detectability]

    A --> A1[Probe Wordlists]
    A --> A2[Vendor Fingerprints]
    A --> A3[Cloud · K8s · CI-CD]
    A --> A4[Secret Catalog]
    A --> A5[Read-Only Validators]
    A --> A6[Email Security]
    A --> A7[Human Intel]
    A --> A8[Sector Notes]

    style Root fill:#dc2626,stroke:#7f1d1d,color:#fff
    style M fill:#1e293b,stroke:#475569,color:#f1f5f9
    style A fill:#7c2d12,stroke:#9a3412,color:#fef3c7
    style M1 fill:#0f172a,stroke:#334155,color:#cbd5e1
    style M2 fill:#0f172a,stroke:#334155,color:#cbd5e1
    style M3 fill:#0f172a,stroke:#334155,color:#cbd5e1
    style M4 fill:#0f172a,stroke:#334155,color:#cbd5e1
    style M5 fill:#0f172a,stroke:#334155,color:#cbd5e1
    style M6 fill:#0f172a,stroke:#334155,color:#cbd5e1
    style A1 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A2 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A3 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A4 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A5 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A6 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A7 fill:#1c1917,stroke:#44403c,color:#fed7aa
    style A8 fill:#1c1917,stroke:#44403c,color:#fed7aa

Engagement Flow

%%{init: {'theme':'base', 'themeVariables': {'primaryColor':'#1e293b','primaryTextColor':'#f1f5f9','primaryBorderColor':'#475569','lineColor':'#94a3b8'}}}%%
flowchart TD
    A["🎯 Target authorized<br/><i>RoE / BB scope / ASM contract</i>"] --> B[methodology<br/>scope check]
    B --> C[methodology<br/>5-stage pipeline]

    C --> D1["🔍 Stage 1<br/>Seed Discovery"]
    C --> D2["🌐 Stage 2<br/>Asset Expansion"]
    C --> D3["📊 Stage 3<br/>Enrichment"]
    C --> D4["⚠️ Stage 4<br/>Exposure Analysis"]
    C --> D5["📋 Stage 5<br/>Reporting"]

    D1 --> E1[DNS catalog<br/>WHOIS / RDAP<br/>public records]
    D2 --> E2[subdomain stack<br/>prefix sweep<br/>Wayback CDX]
    D3 --> E3[vendor fingerprint<br/>identity fabric<br/>infrastructure OSINT]
    D4 --> E4[secret catalog<br/>always-on HTTP checks<br/>K8s exposure<br/>read-only validators<br/>breach × identity]
    D5 --> E5[severity rubric<br/>BB submission<br/>client deliverable]

    E1 --> F[methodology<br/>asset graph]
    E2 --> F
    E3 --> F
    E4 --> G["📋 Findings<br/>severity + confidence + evidence"]
    E5 --> H["📦 Deliverable<br/>exec summary + repro package"]

    F --> G

    style A fill:#3b82f6,color:#fff
    style B fill:#7c2d12,color:#fef3c7
    style C fill:#1e293b,color:#f1f5f9
    style F fill:#7c3aed,color:#fff
    style G fill:#dc2626,color:#fff
    style H fill:#14532d,color:#dcfce7

Usage

With Claude Code

# Install both skills (one-time, after clone)
git clone https://github.com/elementalsouls/Claude-OSINT.git
cd Claude-OSINT
chmod +x ./scripts/sync-skill-content.sh
./scripts/sync-skill-content.sh
mkdir -p ~/.claude/skills
cp -r skills/osint-methodology ~/.claude/skills/
cp -r skills/offensive-osint   ~/.claude/skills/
ls ~/.claude/skills/

Then, in any Claude Code session, ask an OSINT question — both skills auto-load and trigger on relevant phrases (50+ trigger phrases each).

With the Claude Skills System

# Point Claude at a single skill before starting your session
cat skills/offensive-osint/SKILL.md | claude --system-file -

Manual (Claude.ai / Claude API)

Paste the contents of any SKILL.md into a Project's system prompt or prepend it to your conversation. Both files are plain Markdown — also usable as a personal cheat-sheet without Claude.

Authorization

These skills are intended for assets you own or have written authorization to assess (red-team rules of engagement, bug-bounty in-scope assets, ASM contracts).

Both skills include a soft scope-check when you ask Claude to act against an unverified third-party target. They explicitly exclude active exploitation, post-exploitation, malware development, and other activities beyond OSINT-driven reconnaissance. See SECURITY.md for the full posture.

Documentation

Sponsors

Atlas Cloud is a full-modal AI inference platform that gives developers a single AI API to access video generation, image generation, and LLM APIs. Instead of managing multiple vendor integrations, you connect once and get unified access to 300+ curated models across all modalities.

Check out Atlas Cloud's new coding plan promotion for more budget-friendly API access: https://www.atlascloud.ai/console/coding-plan

About

Operational tradecraft accumulated across external attack-surface engagements, codified into Claude skills. Engagement-platform agnostic - slot into any ASM / ticketing / asset-graph platform you already use, or none.

Author: ElementalSoul

Original framework: SnailSploit/offensive-checklist (v1.x)

Inspired by: Bellingcat's Online Investigations Toolkit · IntelTechniques · OSINT Framework

Tool inventory: . ProjectDiscovery · Six2dez reconftw · SecLists · Assetnote Wordlists

License: MIT — use freely, attribution appreciated.

"Give Claude the right skill and it stops being a chatbot. It becomes an operator."