What is find-evil-sift-agent CLAUDE.md?

Project-specific instructions for Claude Code describing a digital-forensics AI agent that investigates evidence using a SIFT Workstation virtual machine.

Use them to set up the agent, inspect disk images and extracted data, run forensic tools, and record investigation findings.

They provide the project structure, evidence locations, setup steps, and case context needed for forensic work.

How OLGTX303/find-evil-sift-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OLGTX303/find-evil-sift-agent. 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/OLGTX303/find-evil-sift-agent/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/OLGTX303/find-evil-sift-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/olgtx303/find-evil-sift-agent/claude-md/github.svg)](https://agentmods.dev/instructions/olgtx303/find-evil-sift-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/olgtx303/find-evil-sift-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/olgtx303/find-evil-sift-agent/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/olgtx303/find-evil-sift-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/olgtx303/find-evil-sift-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,000 This file is loaded in full into every session.

When invoked 1,000 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01000	$0.01000
Opus 5	$0.00500	$0.00500
Sonnet 5	$0.00200	$0.00200
Haiku 4.5	$0.00100	$0.00100

Measured 10d ago against content hash 75196881f27b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

find-evil-sift-agent CLAUDE.md scanned grade B 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

│ └── ssh_client.py ← asyncssh helper with sudo support

CLAUDE.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FIND EVIL! — SIFT Forensic AI Agent

Project structure

sift-agent/
├── orchestrator.py          ← Main autonomous IR agent (gpt-5.4-mini via OpenAI-compatible API)
├── setup_sift_vm.py         ← One-time VM setup: start, share evidence, install deps
├── src/sift_mcp/
│   ├── server.py            ← MCP server exposing SIFT tools
│   ├── tools.py             ← 18 forensic tool implementations (SSH → SIFT VM)
│   └── ssh_client.py        ← asyncssh helper with sudo support
└── findings/                ← Auto-created: agent_execution_log.jsonl + findings_report.json

Evidence (VANKO case)

find/VANKO/surface_physical.E01-E21 — Microsoft Surface 3 disk image (119GB EWF)
find/VANKO/vanko-c-drive.CYLR.7z — Cellebrite C-drive extraction
find/sift-2026-04-22.ova — SIFT Workstation VM

One-time setup

# 1. Import OVA (already done via ovftool)
# VMX at: F:\5Gcase\hackton\SIFT-VM\SIFT-2026\SIFT-2026.vmx

# 2. Install sift-agent
pip install -e .

# 3. Start and configure SIFT VM
python setup_sift_vm.py

# 4. Set environment
set OPENAI_API_KEY=your_key
set OPENAI_BASE_URL=https://api.456478.xyz/
set SIFT_HOST=<vm_ip>
set SIFT_PORT=22      # or 2222 if using NAT
set SIFT_USER=sansforensics
set SIFT_PASS=forensics
set EVIDENCE_DIR=/cases/VANKO

Running the investigation

python orchestrator.py --output-dir ./findings

The agent will autonomously:

Mount the E01 image via ewfmount
Enumerate users and system info
Scan for suspicious executables
Parse registry Run keys (persistence)
Extract logon events from Security.evtx
Run YARA malware detection
Build a timeline with log2timeline
Produce findings/findings_report.json

MCP server (standalone)

# Register in Claude Code
claude mcp add sift-forensic -e SIFT_HOST=<ip> -e SIFT_PORT=22 -- sift-mcp

# Then ask Claude: "Mount the VANKO image and find evil"

Architecture

┌─────────────────────────────────────────────┐
│  Windows Host (Claude Code)                  │
│  orchestrator.py + gpt-5.4-mini (OpenAI-compat API)  │
│  ┌─────────────────────────────────────┐    │
│  │  sift-forensic-mcp (stdio MCP)      │    │
│  │  18 forensic tool definitions        │    │
│  └──────────────┬──────────────────────┘    │
└─────────────────┼───────────────────────────┘
                  │ asyncssh (port 22/2222)
┌─────────────────▼───────────────────────────┐
│  SIFT Workstation VM (VMware NAT)            │
│  Ubuntu 22.04 + 200+ IR tools               │
│  ┌───────────────────────────────────────┐  │
│  │  /cases/VANKO/surface_physical.E01    │  │
│  │  ewfmount → /mnt/ewf/ewf1            │  │
│  │  kpartx   → /dev/mapper/loop0p3      │  │
│  │  /mnt/windows/ (NTFS mounted)         │  │
│  └───────────────────────────────────────┘  │
└─────────────────────────────────────────────┘

Read the full file on GitHub · 103 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.

10d ago First seen · 103 lines · 1,000 tokens per session scan B 75196881f27b

Subscribe to this mod's changes

find-evil-sift-agent CLAUDE.md is an instructions file published in the GitHub repository OLGTX303/find-evil-sift-agent (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,000 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

find-evil-sift-agent: Instructions file for Claude Code