Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aragaobruno/toolbelt --skill cyber-fraud-forensicsgit clone --depth 1 https://github.com/aragaobruno/toolbeltWrote 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/aragaobruno/toolbelt/cyber-fraud-forensics)<a href="https://agentmods.dev/skills/aragaobruno/toolbelt/cyber-fraud-forensics"><img src="https://agentmods.dev/badge/skills/aragaobruno/toolbelt/cyber-fraud-forensics/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/aragaobruno/toolbelt/cyber-fraud-forensics"><img src="https://agentmods.dev/badge/skills/aragaobruno/toolbelt/cyber-fraud-forensics.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 | $0.00106 | $0.01520 |
| Opus 5 | $0.00053 | $0.00760 |
| Sonnet 5 | $0.00021 | $0.00304 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
cyber-fraud-forensics scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cyber-fraud-forensics
SOP for turning a flagged digital-fraud threat (phishing, typosquatting, brand clone) into a clean, evidence-backed abuse report. Scope is technical: how to capture evidence and how to structure the report. It does not assert fixed legal grounds — those are placeholders the operator fills with a verified, current source per jurisdiction.
Scope guardrail
This skill never embeds specific statutes, treaty articles, or "this violates law X" claims as fixed knowledge. Legal/policy citations age badly and a wrong citation weakens a takedown request. Wherever a legal basis is needed, emit a placeholder like [APPLICABLE_LOCAL_LEGISLATION] or [REGISTRAR_ABUSE_POLICY_REF] and flag that it must be filled from a current source. State this limitation in the report itself.
1. Evidence collection
Goal: capture enough that a third party (registrar, host, CERT) can independently verify the site is malicious. Collect read-only; never authenticate, submit, or interact with forms on the suspect site.
Identity & infrastructure
- Suspect URL(s) — full, including path and any redirect chain. Record each hop.
- Resolved IP(s) —
dig +short suspect-domain.com/nslookup. - Hosting / ASN — reverse lookup the IP; note hosting provider and ASN (whois/RDAP).
- Registrar & WHOIS/RDAP — registrar name, creation date (recent registration is a strong signal), and the published abuse contact email — this is the address the report goes to.
- TLS certificate — issuer, validity dates, SANs. A cert covering the spoofed brand name or a mismatched/self-signed cert is evidence.
Network evidence (Chrome DevTools / capture)
Open DevTools on the suspect page and document, with screenshots and exported data:
- Network tab — outbound requests to third-party domains; flag any POST of form data to a domain other than the displayed one (credential exfiltration). Export as HAR.
- External scripts — scripts loaded from unrelated domains, obfuscated JS, known phishing-kit signatures.
- Cookies / storage — suspicious tracking or session-harvesting cookies.
- Console — errors revealing kit origin or backend endpoints.
- Sources — note any cloned assets (logos, CSS) hot-linked from the legitimate brand's domain — direct proof of impersonation.
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.
- 11d ago First seen · 110 lines · 106 tokens per session scan A 771bcdb9a6b5
cyber-fraud-forensics is a skill published in the GitHub repository aragaobruno/toolbelt (2 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 1,520 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ai-project-starter
Use when the user wants to prepare project-specific context engineering documents, AI coding agent instruction files, project starter Markdown files, vibe coding guardrails, PRD/TDD/architecture/security/testing docs, AGENTS.md/CLAUDE.md/Cursor/Windsurf/Continue/Copilot context files, or a complete AI-coding-ready…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
repo-harness
Route explicit repo-harness setup, planning, execution, verification, and handoff actions through deterministic repository state.
report
Investigate bugs comprehensively — cascade through trace, capture browser evidence, extract observability data, and prepare or explicitly create a GitHub issue with grounded findings.