mcp-hayabusa: Skill for Claude Code

.claude/skills/ingest-ti/SKILL.md

ingest-ti is a skill for Claude Code from omeryemba/mcp-hayabusa. It costs 60 tokens per session (1,486 once invoked), scanned A, original, MIT.

A skill for importing threat-intelligence indicators, such as IP addresses, domains, file hashes, and URLs, from JSON files. It converts them to one consistent format and compares them across sources and Sigma detection rules.

In plain words
What is it for?
Normalizing IOC data, finding duplicates or overlaps between sources, checking Sigma rule coverage, and optionally comparing saved scan results.
Why use it?
It removes the need to hand-convert different indicator formats before comparing or investigating them.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is omeryemba/mcp-hayabusa's own configuration. It tells Claude Code how to work on mcp-hayabusa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-hayabusa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to omeryemba/mcp-hayabusa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/omeryemba/mcp-hayabusa/master/.claude/skills/ingest-ti/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/omeryemba/mcp-hayabusa

Made for: Claude Code.

Wrote 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.

agentmods badge for ingest-ti

README.md
[![agentmods](https://agentmods.dev/badge/skills/omeryemba/mcp-hayabusa/ingest-ti/github.svg)](https://agentmods.dev/skills/omeryemba/mcp-hayabusa/ingest-ti)
Your own site
<a href="https://agentmods.dev/skills/omeryemba/mcp-hayabusa/ingest-ti"><img src="https://agentmods.dev/badge/skills/omeryemba/mcp-hayabusa/ingest-ti/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.

agentmods 80×15 button for ingest-ti

Your own site · 80×15
<a href="https://agentmods.dev/skills/omeryemba/mcp-hayabusa/ingest-ti"><img src="https://agentmods.dev/badge/skills/omeryemba/mcp-hayabusa/ingest-ti.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,486 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.01486
Opus 5 $0.00030 $0.00743
Sonnet 5 $0.00012 $0.00297
Haiku 4.5 $0.00006 $0.00149

Measured 10d ago against content hash 664b7c6a9bbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ingest-ti 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/correlate_ti.py, scripts/ingest_ti.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/ingest-ti/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Intelligence Ingestion & Correlation

Ingests IOC data from local files, normalizes every indicator to a common schema, then correlates it — across multiple TI sources, against this project's installed Sigma rule coverage, and optionally against a saved Hayabusa scan/timeline result — via two deterministic scripts. This is the backing skill for the /ingest-ti command (.claude/commands/ingest-ti.md).

Normalized IOC schema

Every indicator, regardless of source format, is normalized to exactly these fields (all keys always present; a value may be null, but the key isn't dropped):

{
  "type": "ip",
  "value": "1.2.3.4",
  "confidence": 0.8,
  "source": "native:watchlist",
  "first_seen": "2026-01-01T00:00:00Z",
  "attack_technique": "T1071.001",
  "notes": "category=Network activity; comment=C2 IP"
}

type is a closed set: ip, domain, hash, url, other. An entry with an unrecognized type is coerced to other (not dropped); an entry missing value entirely is skipped (it can't be correlated on anything).

How to apply

  1. Ingest each source file separately with ingest_ti.py — one file in, one normalized JSON report out. Never hand-parse a TI file's JSON yourself; the format-detection and normalization logic here is deterministic and already handles both supported formats' edge cases (MISP type mapping, epoch timestamp conversion, missing-field defaulting).
  2. Correlate normalized reports together with correlate_ti.py — takes 1+ of ingest_ti.py's output files, merges/dedupes IOCs sharing a (type, value) key across sources, and checks every referenced ATT&CK technique against this project's installed Sigma rules via analyze_coverage/suggest_rule (mcp_hayabusa.knowledge — the same functions backing this project's analyze_coverage/suggest_rule MCP tools, not reimplemented here).
  3. Optionally correlate against local evidence by passing --hayabusa-result <path> to correlate_ti.py, pointing at a JSON file already saved to disk from a prior Hayabusa MCP tool call (scan_evtx, hayabusa_csv_timeline, hayabusa_json_timeline, etc.) — each merged indicator's value is then substring-matched against that file's raw text.

Read the full file on GitHub · 69 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 69 lines · 60 tokens per session scan A 664b7c6a9bbf

Subscribe to this mod's changes

ingest-ti is a skill published in the GitHub repository omeryemba/mcp-hayabusa (0 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,486 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

analyzing-windows-prefetch-with-python

Parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns.

26zl/cybersec-toolkit · 43 tokens

Blue Team Defense & Hardening

System hardening, detection engineering, security baseline monitoring, patch management, defense-in-depth architecture, and security posture improvement.

Masriyan/Claude-Code-CyberSecurity-Skill · 30 tokens

analyzing-ransomware-encryption-mechanisms

Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery efforts. Covers AES, RSA, ChaCha20, and hybrid encryption schemes. Activates for requests involving ransomware…

26zl/cybersec-toolkit · 79 tokens

analyzing-slack-space-and-file-system-artifacts

Examine file system slack space, MFT entries, USN journal, and alternate data streams to recover hidden data and reconstruct file activity on NTFS volumes.

26zl/cybersec-toolkit · 44 tokens

conducting-external-reconnaissance-with-osint

Conducts external reconnaissance using Open Source Intelligence (OSINT) techniques to map an organization's external attack surface without directly interacting with target systems. The tester gathers information from public sources including DNS records, certificate transparency logs, search engines, social media…

26zl/cybersec-toolkit · 96 tokens

conducting-mobile-app-penetration-test

Conducts penetration testing of iOS and Android mobile applications following the OWASP Mobile Application Security Testing Guide (MASTG) to identify vulnerabilities in data storage, network communication, authentication, cryptography, and platform-specific security controls. The tester performs static analysis of…

26zl/cybersec-toolkit · 108 tokens