Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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.
| Date | Stars |
|---|---|
| 2026-07-31 | 2026 |
| 2026-08-06 | 2026 |
| 2026-08-11 | 2269 |
| 2026-08-18 | 2305 |
| 2026-08-19 | 2307 |
| 2026-08-20 | 2313 |
| 2026-08-21 | 2317 |
| 2026-08-22 | 2321 |
| 2026-08-23 | 2324 |
| 2026-08-24 | 2331 |
| 2026-08-25 | 2335 |
| 2026-08-26 | 2340 |
| 2026-08-27 | 2344 |
| 2026-08-28 | 2345 |
| 2026-08-29 | 2350 |
| 2026-08-30 | 2354 |
| 2026-08-31 | 2357 |
| 2026-09-01 | 2441 |
| 2026-09-02 | 2494 |
| 2026-09-03 | 2519 |
| 2026-09-04 | 2532 |
| 2026-09-05 | 2539 |
| 2026-09-06 | 2548 |
| 2026-09-07 | 2562 |
| 2026-09-08 | 2568 |
| 2026-09-09 | 2579 |
| 2026-09-10 | 2584 |
| 2026-09-11 | 2588 |
| 2026-09-12 | 2594 |
| 2026-09-13 | 2601 |
| 2026-09-14 | 2605 |
| 2026-09-15 | 2612 |
| 2026-09-16 | 2618 |
| 2026-09-17 | 2621 |
| 2026-09-18 | 2626 |
| 2026-09-19 | 2627 |
| 2026-09-20 | 2632 |
Today
+5 stars today
This week
+31 stars this week
This month
+315 stars this month
Momentum
51.0
growth rate 1.19%/day
# 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.
Built by **[Sachin Sharma](https://www.linkedin.com/in/sachinsharma8080/)** — GenAI Security Research.
<p align="center">
<sub>SPONSORED BY</sub>
<br/>
<a href="https://www.atlascloud.ai/console/coding-plan">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="assets/sponsors/atlas-cloud-dark.svg">
<img alt="Atlas Cloud" src="assets/sponsors/atlas-cloud-light.svg" height="36">
</picture>
</a>
<a href="https://threatwatch360.com">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="assets/sponsors/tw360-dark.svg">
<img alt="ThreatWatch360" src="assets/sponsors/tw360-light.svg" height="30">
</picture>
</a>
</p>
---
## What is this?
`claude-osint` is a library of skills for the [Claude skills system](https://docs.claude.com/en/docs/claude-code/skills). Each skill is a structured `SKILL.md` file that primes Claude with expert-level methodology for one part of the offensive recon problem.
**The core pair — the recon backbone:**
- **`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.
**Six organization-grade depth skills — enterprise-scale attack-surface reasoning the core pair doesn't carry:**
- **`org-attack-surface`** - legal entity → owned footprint (GLEIF org-tree, org-first RIR "dark netblock" recall, ASN hyperscaler-scope guard). Discover-only.
- **`email-domain-security`** - composite spoofability verdict (envelope vs header-From; SPF `-all` alone ≠ spoof-proof) + SPF supply-chain analysis.
- **`exposure-risk-quantification`** - FAIR 0–100 + A–F risk score, $-denominated loss model, board one-pager, ownership/proof honesty caps.
- **`continuous-exposure-monitoring`** - re-scan/diff loop + CTI/ransomware chatter + finding-lifecycle FP discipline + durable alert outbox.
- **`cloud-saas-exposure`** - bucket ownership-gated severity + offline AWS account-ID decode + dependency-confusion confirmation + K8s/CI fingerprint.
- **`identity-provider-recon`** - tenant/federation mapping + pre-auth user-enumeration oracle + name×pattern login synthesis, with a hard enumeration boundary.
Drop them 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.
~10,000 lines of structured tradecraft · **56/56 PASS** on a 56-prompt self-evaluation (100%, zero fabrications) · ~85–90% practitioner coverage for the recon phase of authorized engagements.
---
## Structure
```
claude-osint/
├── skills/
│ ├── osint-methodology/SKILL.md # how to think (515 lines)
│ ├── offensive-osint/
│ │ ├── SKILL.md # what to reach for (4,555 lines)
│ │ ├── scripts/secret_scan.py # stdlib-only 80-pattern secret scanner
│ │ └── scripts/h1_reference.py # HackerOne disclosed-reports reference agent
│ ├── org-attack-surface/SKILL.md # legal entity → owned footprint (1,052 lines)
│ ├── email-domain-security/SKILL.md # spoofability + SPF supply-chain (589 lines)
│ ├── exposure-risk-quantification/SKILL.md # FAIR $ risk score + board one-pager (748 lines)
│ ├── continuous-exposure-monitoring/SKILL.md # re-scan/diff + CTI chatter (811 lines)
│ ├── cloud-saas-exposure/SKILL.md # cloud + supply-chain depth (80Excerpt of 22,663 characters
Read on GitHub
22
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:48b1e01bce3adbe2, llm:Repository description: 'Two paired Claude skills · 90+ recon modules · 48 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · 5,500+ 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.' Topics: agentskills, claude, skills.
matched fp:48b1e01bce3adbe2, llm:Repository description: 'Two paired Claude skills · 90+ recon modules · 48 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · 5,500+ 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.' Topics: agentskills, claude, skills.