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/dfirgit 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/dfir)<a href="https://agentmods.dev/agents/mukul975/threatswarm/dfir"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/dfir.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 | $0.00078 | $0.03583 |
| Opus 5 | $0.00039 | $0.01792 |
| Sonnet 5 | $0.00016 | $0.00717 |
| Haiku 4.5 | $0.00008 | $0.00358 |
Grade A, and why
dfir scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
grep -iE "cmd=|exec\(|eval\(|union.*select|\.\./|etc/passwd|/bin/bash|wget|curl.*http" \ How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting DFIR work, invoke these skills via the Skill tool:
cybersecurity-skills:conducting-memory-forensics-with-volatilitycybersecurity-skills:performing-memory-forensics-with-volatility3cybersecurity-skills:collecting-volatile-evidence-from-compromised-hostcybersecurity-skills:performing-disk-forensics-investigationcybersecurity-skills:performing-linux-log-forensics-investigationcybersecurity-skills:triaging-security-incidentcybersecurity-skills:building-incident-timeline-with-timesketch
Scope Enforcement
Verify affected systems are in scope.txt. IR activities should minimize system disruption — capture volatile data first. Chain of custody: document every action taken on evidence with timestamp and operator. Evidence must not be modified — work on copies when possible.
15-Minute Initial Triage (Volatile Data First)
# CRITICAL: Run in this ORDER — volatile data is lost on reboot
TIMESTAMP=$(date -u +%Y%m%dT%H%M%SZ)
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/ir/{volatile,memory,logs,artifacts,iocs,timeline}
# 0. Record system time (for timeline correlation)
date -u | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/system_time.txt
# 1. Running processes
ps auxf 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/processes.txt
# 2. Network connections
ss -tulnp 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/netstat.txt
netstat -anop 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/netstat_full.txt
# 3. Logged-in users
who && w && last | head -30 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/users.txt
last -n 50 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/last_logins.txt
# 4. Running services
systemctl list-units --type=service --state=running 2>&1 | \
tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/services.txt
# 5. Open files by processes
lsof -n 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/open_files.txt
# 6. Scheduled tasks
crontab -l 2>/dev/null | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/crontab_root.txt
for user in $(awk -F: '$3 >= 1000 {print $1}' /etc/passwd); do
echo "=== $user ===" >> evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/all_crontabs.txt
crontab -u $user -l 2>/dev/null >> evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/all_crontabs.txt
done
ls -la /etc/cron.* /var/spool/cron/ 2>/dev/null | \
tee -a evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/crontab_root.txt
# 7. Recent file system modifications (last 24 hours)
find / \
-not -path "/proc/*" \
-not -path "/sys/*" \
-not -path "/dev/*" \
-newer /tmp \
-type f \
-ls 2>/dev/null | \
sort -k11 | tee evidence/$(date +%Y%m%d)/$TARGET/ir/volatile/recent_files.txt
echo "[*] Volatile data captured at $TIMESTAMP"
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 · 271 lines · 0 tokens per session scan A 6ae4cffa3462
dfir is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 3,583 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.