# elementalsouls/Claude-OSINT

8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 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.

Repository: https://github.com/elementalsouls/Claude-OSINT
Canonical: https://ross.abutalabs.com/products/claude-osint
Language: Python
License: MIT
License Family: permissive
Topics: agentskills, claude, skills
Last push: 2026-08-24T16:21:23+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 9
- inputs: {"age_days": 129, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2342, forks 435 (observed 2026-08-28T04:06:38.969128+00:00)

## What it is
A collection of eight drop-in SKILL.md files for the Claude skills system that prime Claude with expert offensive OSINT and external recon methodology. It covers asset discovery, email/domain security, exposure risk quantification, cloud/SaaS exposure, and identity-provider recon for authorized red-team and bug-bounty engagements.

## Use cases
- run osint recon on a target domain with claude
- map an organization's external attack surface
- check email spoofability and spf misconfigurations
- find leaked secrets and credentials in public sources
- quantify exposure risk for a board report
- enumerate cloud and saas exposure for a company
- prepare attack paths for a bug bounty engagement

## When to choose
- you use Claude Code or the Claude skills system and need structured recon methodology
- you run authorized red-team or bug-bounty engagements and want repeatable tradecraft
- you want curated regexes, dorks, and validator workflows without building them yourself

## When to avoid
- you need a standalone scanner or automated tool rather than LLM-guided methodology
- your use case is unauthorized reconnaissance or attacks outside a legal scope
- you don't use Claude or another LLM agent that supports skill files

## Facets
- artifact type: learning-resource
- maturity: active
- function: osint, security, penetration-testing, prompt-engineering, agent-framework
- domain: security, osint, penetration-testing, developer-tools, artificial-intelligence
- platform: python, cli, cross-platform
- tags: claude-skills, recon, red-team, bug-bounty, attack-surface, skill-md, tradecraft, prompt-library

## Member repositories
- elementalsouls/Claude-OSINT (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:38.969128+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:37:17.199816+00:00, confidence not recorded.
  - readme: https://github.com/elementalsouls/Claude-OSINT (fetched 2026-08-28T04:06:38.969128+00:00, sha 87f572d829ef)
- Data as of 2026-08-30T08:39:29.467469+00:00.