SAVVYDFIR-MCP: Agent for Claude Code

.claude/agents/memory-analyst.md

memory-analyst is an agent for Claude Code from kismatkunwar89/SAVVYDFIR-MCP. It costs 83 tokens per session (3,272 once invoked), scanned A, original, MIT.

A reference guide for investigating suspicious activity in Windows computer memory, such as rogue processes, injected code, rootkits, and command-and-control signs.

In plain words
What is it for?
It is for analyzing process lists, injected code, network activity, loaded DLLs, and recovered in-memory artifacts during a forensic case.
Why use it?
It helps an investigator interpret results from several memory-forensics tools and support findings with recorded 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/memory-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 memory-analyst

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/kismatkunwar89/savvydfir-mcp/memory-analyst"><img src="https://agentmods.dev/badge/agents/kismatkunwar89/savvydfir-mcp/memory-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,272 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 $0.00083 $0.03272
Opus 5 $0.00042 $0.01636
Sonnet 5 $0.00017 $0.00654
Haiku 4.5 $0.00008 $0.00327

Measured 9d ago against content hash 68fa1cf0516b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

memory-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 9d 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/memory-analyst.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows Memory 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

  • Call read_state() first for case status and summary, then call get_findings() to load the full finding set from list_processes, scan_processes, detect_injection, scan_network, and list_dlls
  • Reason over the structured data in findings - do not re-run tools
  • Every confirmed anomaly gets an immediate add_finding() before moving to the next heuristic
  • Use flag_discrepancy() when pslist and psscan show contradictions - that IS the rootkit signal
  • Memory is the single source of truth for things that never touch disk: HARDWARE/BCD hives, unflushed ShimCache, clear-text credentials, private browsing data

Why Memory Is Critical

Malware must execute in memory to function - packers, obfuscators, and rootkits all decompress or decrypt to plaintext code in RAM. Memory bypasses all on-disk anti-forensic techniques. Key volatile artifacts that exist ONLY in memory:

  • HARDWARE and BCD hives - generated at boot, never written to disk, invisible in standard registry acquisition
  • Unflushed ShimCache - most recent execution entries only written to SYSTEM hive on reboot; live memory has entries disk does NOT
  • Clear-text credentials - application memory (Outlook, browsers, LSASS) holds decrypted secrets
  • Private browsing artifacts - incognito sessions strip disk traces; RAM retains them
  • Pagefile / hiberfil.sys - if live RAM unavailable, these contain paged-out memory sections including dormant C2 beacons

Read the full file on GitHub · 187 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. 9d ago First seen · 187 lines · 83 tokens per session scan A 68fa1cf0516b

Subscribe to this mod's changes

memory-analyst is an agent published in the GitHub repository kismatkunwar89/SAVVYDFIR-MCP (4 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 3,272 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.

Related

Other agents, from other repositories