Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Orizon-eu/claude-code-pentestnpx agentmods add skills/orizon-eu/claude-code-pentest/attack-path-architectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/orizon-eu/claude-code-pentest/attack-path-architect)<a href="https://agentmods.dev/skills/orizon-eu/claude-code-pentest/attack-path-architect"><img src="https://agentmods.dev/badge/skills/orizon-eu/claude-code-pentest/attack-path-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/orizon-eu/claude-code-pentest/attack-path-architect"><img src="https://agentmods.dev/badge/skills/orizon-eu/claude-code-pentest/attack-path-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.01809 |
| Opus 5.5 | $0.00041 | $0.00724 |
| Sonnet 5.5 | $0.00020 | $0.00362 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade C, and why
attack-path-architect scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
| +-- Step 2: Access cloud metadata (169.254.169.254) How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack Path Architect
Strategic attack path generator. Transforms reconnaissance data into actionable kill chains mapped to MITRE ATT&CK.
Important
CRITICAL: This skill is for authorized penetration testing and red team engagements ONLY. Confirm authorization before generating attack paths.
Instructions
Step 1: Input Collection
Accept one of these inputs:
- Recon JSON data from recon-dominator (consolidated.json or individual module outputs)
- Raw domain - will perform lightweight recon first to gather data
- Manual asset list - user provides hostnames, IPs, services, technologies
If the user provides only a domain, run a quick recon summary first using recon-dominator scripts, then proceed.
Step 2: Asset Classification
python scripts/classify_assets.py --input {recon_data}
Classify every discovered asset by:
Exposure Level:
- EXTERNAL: Internet-facing, directly reachable
- SEMI-EXTERNAL: Behind CDN/WAF but still reachable
- INTERNAL-EXPOSED: Internal service accidentally exposed (common with cloud misconfig)
Asset Type:
- WEB_APP: Web applications (highest attack surface)
- API: REST/GraphQL/SOAP endpoints
- MAIL: Email infrastructure
- DNS: DNS servers
- VPN: VPN gateways
- DATABASE: Exposed database services
- ADMIN_PANEL: Management interfaces
- CI_CD: Build/deploy infrastructure
- MONITORING: Grafana, Kibana, Prometheus, etc.
- STORAGE: S3, GCS, Azure Blob, etc.
- LEGACY: Old/deprecated systems still running
Risk Score (1-10): Based on technology age, known CVE count, misconfiguration signals, exposure level.
Step 3: Trust Relationship Mapping
python scripts/map_trust.py --input {recon_data}
Identify trust relationships between assets:
- SSO/OAuth connections: Shared authentication across subdomains
- Cookie scope: Wildcard cookies (.domain.com) enabling session sharing
- API dependencies: Internal APIs called by external apps
- DNS relationships: CNAME chains, shared nameservers
- Certificate sharing: Shared TLS certificates (SAN entries)
- IP proximity: Assets in same subnet/ASN suggesting shared infrastructure
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 203 lines · 102 tokens per session scan C 6e6bac20e696
attack-path-architect is a skill published in the GitHub repository Orizon-eu/claude-code-pentest (28 stars, last pushed 7mo ago), licensed MIT. It adds 102 tokens to every session and 1,809 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
forensics-kit
Digital forensics and incident response toolbox. Load when the operator asks about a pcap, a binary, a memory dump, a suspicious file, malware triage, IOC hunting, or post-incident analysis. Covers network (tshark), binaries (radare2, strings, binwalk, file, exiftool), memory (volatility), and pattern matching (YARA).…
passive-osint
Passive reconnaissance against a target without sending traffic that could alert it. Load when the engagement starts, when you only know a domain/email/username, when scope is unclear, or when you need historical surface area. Covers subdomain enumeration (crt.sh, subfinder), historical archives (wayback), DNS posture…
bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…
mobile-pentest
Mobile app pentest for bug bounty (Android APK + iOS IPA) — runtime-first workflow: install app, proxy through Burp/mitmproxy, drive the UI, capture packets, then test the API exactly like a web target; escalate to decompile (apktool/jadx) and Frida/objection only when traffic is SSL-pinned, encrypted, or absent.…
hunt-api-misconfig
Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {isadmin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT signature/crypto forging (alg:none, key confusion, kid/jku) is owned by hunt-jwt-crypto; this…
hunt-ato
Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session…