Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ogrodev/fsociety/classifygit clone --depth 1 https://github.com/ogrodev/fsocietyWhat 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 | $0.00014 | $0.00792 |
| Opus 5 | $0.00007 | $0.00396 |
| Sonnet 5 | $0.00003 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
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 2d 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.
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, orUPX!magic - ASPack: Section name
.aspackor.adata - Themida: Section name
.winlicenseor.themida - VMProtect: Section name
.vmp0,.vmp1 - .NET Reactor:
.reactosection - Enigma Protector:
.enigmasection
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
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.
- 2d ago First seen · 105 lines · 14 tokens per session scan A fdb0f3fcc8b7
classify is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 792 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
pr
Create a PR to main branch using conventional commit style for the title.
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.
pentest-exit
Close pentest session — summarizes findings, ensures outputs are saved, lifts isolation, and prompts for /clear.
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.
bb-spray
Credential spraying across discovered services.
checklist
Generate a custom checklist for the current feature based on user requirements.