SAVVYDFIR-MCP: Agent for Claude Code

.claude/agents/evtx-analyst.md

evtx-analyst is an agent for Claude Code from kismatkunwar89/SAVVYDFIR-MCP. It costs 84 tokens per session (4,695 once invoked), scanned A, original, MIT.

A Windows event-log forensics specialist for Security, System, and Sysmon logs. Windows event logs record activity such as sign-ins, process launches, and system changes.

In plain words
What is it for?
Use it to investigate authentication problems, movement between computers, stolen credentials, persistence, hiding activity, and NTLM or Kerberos attacks.
Why use it?
It helps investigators examine attacker activity without loading entire log files into the working context and keeps findings tied to specific evidence.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is kismatkunwar89/SAVVYDFIR-MCP's own configuration. It tells Claude Code how to work on SAVVYDFIR-MCP 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 SAVVYDFIR-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kismatkunwar89/SAVVYDFIR-MCP. 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/kismatkunwar89/SAVVYDFIR-MCP/master/.claude/agents/evtx-analyst.md
Clone the repo
git clone --depth 1 https://github.com/kismatkunwar89/SAVVYDFIR-MCP

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 evtx-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/evtx-analyst/github.svg)](https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/evtx-analyst)
Your own site
<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/evtx-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/evtx-analyst/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 evtx-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/evtx-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/evtx-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,695 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 $0.00084 $0.04695
Opus 5 $0.00042 $0.02348
Sonnet 5 $0.00017 $0.00939
Haiku 4.5 $0.00008 $0.00470

Measured 10d ago against content hash 526c99b42103, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

evtx-analyst 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.

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/agents/evtx-analyst.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows Event Log Forensic Analyst

How this file is used

This is a forensic-heuristic knowledge base, not a procedural playbook. The main investigator agent reads this file as reference context when analyzing the relevant artifact. Apply heuristics where they fit the case context - do not execute them as a fixed sequence.

For court-defensible findings: cite the specific tool execution and raw evidence that supports each claim. Use submit_finding with structured provenance (execution_id, evidence_excerpt, contradictions, corroborations).

The user-authored heuristics below were preserved verbatim during the 2026-05-23 Phase 3 overlay removal.

Forensic Ground Rules

  • NEVER load raw CSV rows into context - write targeted Pandas queries via run_analysis only
  • Schema discovery is mandatory first - EvtxECmd column names vary by version and channel
  • Every confirmed anomaly gets an immediate add_finding call before the next query
  • Call read_state first for case status and attack-window summary, then call get_findings when you need the full prior MFT/registry finding set
  • Raw .evtx files copied from a live system may lack template context - if descriptions appear empty, the CSV may only have structured XML fields; hunt by EventId column directly
  • Always check VSS-sourced logs if available - live logs may be truncated or cleared; VSS extends the event horizon

What the Event Logs Tell You

Windows event logs are spread across multiple channels - understanding which log holds what matters:

  • Security.evtx: authentication, logon/logoff, privilege use, object access, policy changes - primary investigation target
  • System.evtx: service installation (7045), crashes (7034), time changes (1/6013), log cleared (104)
  • Application.evtx: application crashes (1000/1002) - malware and injectors frequently crash legitimate processes
  • Sysmon: process creation with full command lines, network connections, file creation, registry changes - highest fidelity source
  • TerminalServices-RDPClient.evtx: outbound RDP connections (1024/1102/1029) - reveals WHERE the victim machine connected to
  • RDPCoreTS: inbound RDP (131) - captures connecting source
  • Microsoft-Windows-Partition/Diagnostic.evtx: USB VID/PID/VSN/capacity - can prove device was reformatted between uses (VSN changes on format)

Read the full file on GitHub · 345 lines

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 · 345 lines · 84 tokens per session scan A 526c99b42103

Subscribe to this mod's changes

evtx-analyst is an agent published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 4,695 once invoked, about $0.0004 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.