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/decompilegit 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 | $0.00011 | $0.00622 |
| Opus 5 | $0.00005 | $0.00311 |
| Sonnet 5 | $0.00002 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade B, and why
decompile 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
If missing, inform user and suggest: `sudo apt install -y ghidra` How it starts
The opening of the file, as written. The whole thing — 71 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.
Ghidra Headless Decompilation
Parse $ARGUMENTS for the binary path and optional --function <name> flag.
Pre-flight
-
Verify Ghidra is installed:
node "${CLAUDE_PLUGIN_ROOT}/scripts/tool-checker.js" check ghidraIf missing, inform user and suggest:
sudo apt install -y ghidra -
Locate
analyzeHeadless:find /opt/ghidra* /usr/share/ghidra -name analyzeHeadless 2>/dev/null | head -1
Step 1 — Create Project Directory
mkdir -p extracted/ghidra-projects
Step 2 — Run Headless Analysis
analyzeHeadless extracted/ghidra-projects ProjectName \
-import <binary> \
-overwrite \
-analysisTimeoutPerFile 300 \
-postScript ExportDecompilation.java \
-scriptPath /path/to/scripts
If ExportDecompilation script is not available, use radare2 as fallback:
r2 -qc 'aaa; pdd @main' <binary> # Decompile main
r2 -qc 'aaa; afl~[0]' <binary> # List function addresses
r2 -qc 'aaa; pdd @<addr>' <binary> # Decompile specific function
Step 3 — Targeted Decompilation
If --function <name> was specified:
r2 -qc 'aaa; s <name>; pdd' <binary>
Step 4 — Key Function Identification
Focus on functions that reference:
- Network:
WSAStartup,connect,send,recv,InternetOpen,HttpSendRequest - File I/O:
CreateFile,WriteFile,DeleteFile,CopyFile - Process:
CreateProcess,VirtualAlloc,WriteProcessMemory,CreateRemoteThread - Registry:
RegCreateKey,RegSetValue,RegOpenKey - Crypto:
CryptEncrypt,CryptDecrypt,BCryptGenRandom - Anti-Debug:
IsDebuggerPresent,NtQueryInformationProcess,CheckRemoteDebuggerPresent
Step 5 — Save Output
Save decompiled code to extracted/decompiled-<binary-name>/.
Generate summary with key functions annotated.
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 · 71 lines · 11 tokens per session scan B 48a59c9e1f66
decompile is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 622 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
pr
Create a PR to main branch using conventional commit style for the title.
engage.scope
Execute Phase 0 - Scope Definition and Rules of Engagement.
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.