classify

classify is a command for Claude Code from ogrodev/fsociety. It costs 14 tokens per session (792 once invoked), scanned A, original, MIT.

A malware-analysis command for examining a binary file, such as a program file. It hashes the file, measures data randomness, checks for packer signatures, and uses tools such as YARA, radare2, or pefile.

In plain words
What is it for?
Use it to identify a binary, inspect entropy by section, detect known packers such as UPX or Themida, and support a malware classification review.
Why use it?
It gathers several clues that can indicate whether a binary is compressed, obfuscated, encrypted, or packed. It also keeps generated output in the project directory according to its storage rule.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the romero plugin — 5 skills, 10 commands, 1 agent shipped together

Good fit Use it to identify a binary, inspect entropy by section, detect known packers such as UPX or Themida, and support a malware classification review.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ogrodev/fsociety
Claude Code
/plugin install romero

Made for: Claude Code.

Or install romero, the plugin that ships this one along with the rest of its 5 skills, 10 commands, 1 agent.

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 classify

README.md
[![agentmods](https://agentmods.dev/badge/commands/ogrodev/fsociety/classify/github.svg)](https://agentmods.dev/commands/ogrodev/fsociety/classify)
Your own site
<a href="https://agentmods.dev/commands/ogrodev/fsociety/classify"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/classify/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 classify

Your own site · 80×15
<a href="https://agentmods.dev/commands/ogrodev/fsociety/classify"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/classify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 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 $0.00014 $0.00792
Opus 5.5 $0.00006 $0.00317
Sonnet 5.5 $0.00003 $0.00158
Haiku 4.5 $0.00001 $0.00079

Measured 1mo ago against content hash fdb0f3fcc8b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

classify 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 1mo 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.

romero/commands/classify.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Storage Policy: ALL output files MUST be saved in the project directory. NEVER write to /tmp/ or any system temporary directory.

Malware Classification

Parse $ARGUMENTS to get the binary path.

Step 1 — Hash & Identify

node "${CLAUDE_PLUGIN_ROOT}/scripts/binary-hasher.js" hash "$ARGUMENTS"

Step 2 — Entropy Analysis

Use radare2 for per-section entropy:

r2 -qc 'iS~entropy' <binary>

Or use Python pefile:

python3 -c "
import pefile, math
pe = pefile.PE('$ARGUMENTS')
for s in pe.sections:
    data = s.get_data()
    if len(data) == 0: continue
    entropy = 0
    for x in range(256):
        p = data.count(bytes([x])) / len(data)
        if p > 0: entropy -= p * math.log2(p)
    name = s.Name.decode().rstrip('\x00')
    print(f'{name}: entropy={entropy:.2f} size={len(data)}')
"

Interpretation:

  • 0-1: Empty/null data
  • 1-5: Normal code/data
  • 5-7: Compressed or obfuscated
  • 7-8: Encrypted or packed (HIGH confidence)

Step 3 — Packer Detection

Known packer signatures:

  • UPX: Section names UPX0, UPX1, or UPX! magic
  • ASPack: Section name .aspack or .adata
  • Themida: Section name .winlicense or .themida
  • VMProtect: Section name .vmp0, .vmp1
  • .NET Reactor: .reacto section
  • Enigma Protector: .enigma section

Check with file:

file <binary> | grep -i "packed\|UPX\|compressed"

Step 4 — YARA Scan

yara -r /usr/share/yara/rules/ <binary> 2>/dev/null
yara -r /opt/yara-rules/ <binary> 2>/dev/null

If no YARA rules are installed, note this and suggest installing community rulesets.

Step 5 — ssdeep Similarity

ssdeep <binary>

Compare against known samples if a reference database exists.

Step 6 — IOC Extraction

From strings and structure, extract:

  • C2 server addresses (URLs, IPs)
  • Mutex names (unique identifiers)
  • Dropped file paths
  • Registry persistence keys
  • Scheduled task names
  • Service names

Read the full file on GitHub · 105 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. 1mo ago First seen · 105 lines · 14 tokens per session scan A fdb0f3fcc8b7

Subscribe to this mod's changes

classify is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 792 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

Other commands, from other repositories

pentest

Activate pentest mode — displays ASCII art, configures session isolation, collects engagement scope, then OWNS the engagement: pre-flight, recon, planning (via the pentester-orchestrator planner), executor dispatch, a time-budget quota loop, aggregation, and report generation.

Stickman230/claude-pentest · 58 tokens

pentest-attacks

Define the attack profile for an engagement — select which attack categories and skills to use. Saves to .pentest-attacks.json. If run before /pentest:pentest, the orchestrator will respect the selection. If run standalone, does not launch a pentest.

Stickman230/claude-pentest · 60 tokens

pentest-scope

Define or update engagement scope — saves scope to disk without launching a pentest. Can be run before or during an engagement. If a pentest is active and the target changes drastically, warns the operator and suggests a new engagement.

Stickman230/claude-pentest · 51 tokens

pentest-kali

Connect to a Metasploit-Kali Server (MKS) REST API — verifies connectivity, discovers available Kali tools, and configures agents to prefer MKS endpoints over local Bash equivalents.

Stickman230/claude-pentest · 43 tokens

pentest-exit

Close pentest session — summarizes findings, ensures outputs are saved, lifts isolation, and prompts for /clear.

Stickman230/claude-pentest · 26 tokens

bb-ad

Active Directory enumeration and attack techniques. Includes LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP Roasting), SMB attacks, and domain privilege escalation. Use this when targeting Windows domain environments.

allsmog/blackbox-claude-plugin · 44 tokens