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/mukul975/threatswarm/irgit 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/commands/mukul975/threatswarm/ir)<a href="https://agentmods.dev/commands/mukul975/threatswarm/ir"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/ir.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 5.1 | $0.00015 | $0.00860 |
| Opus 5 | $0.00008 | $0.00430 |
| Sonnet 5 | $0.00003 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
ir 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 5d 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.
What it actually says
Run incident response workflow for: $ARGUMENTS
Parse $ARGUMENTS: incident type is one of [compromise, ransomware, data-exfil, insider, malware, unknown] Optional second argument: affected system IP or hostname.
-
IR Kickoff:
═══════════════════════════════════════════════════ INCIDENT RESPONSE START Type: $ARGUMENTS Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ) Operator: $(whoami) ═══════════════════════════════════════════════════Create directories:
mkdir -p evidence/$(date +%Y%m%d)/IR_$(date +%H%M%S)/{volatile,memory,logs,artifacts,iocs,timeline} IR_DIR=evidence/$(date +%Y%m%d)/IR_$(date +%H%M%S) -
Type-Specific Checklist:
compromise: Focus on initial access vector, persistence, lateral movement, credential theft ransomware: Focus on initial infection vector, encryption scope, shadow copy deletion, C2 communication data-exfil: Focus on data accessed, exfiltration method, destination IPs/domains insider: Focus on privileged access abuse, data downloads, account activity timeline malware: Focus on malware family identification, persistence, C2, affected hosts
-
Invoke
dfirAgent: Delegate full triage with:- Incident type context
- Volatile data capture first (processes, network, users)
- Persistence mechanism hunting
- Memory acquisition guidance (avml/LiME)
- Log collection and analysis
- Evidence directory:
$IR_DIR
-
System Snapshot: Capture current state:
# Snapshot current processes, network, users ps auxf > $IR_DIR/volatile/processes_$(date +%s).txt ss -tulnp > $IR_DIR/volatile/network_$(date +%s).txt who > $IR_DIR/volatile/users_$(date +%s).txt -
IOC Extraction: Extract all IOCs to
$IR_DIR/iocs/:- IP addresses from logs and network connections
- Domain names from DNS and web logs
- File hashes of suspicious executables
- Registry keys (Windows), cron entries (Linux)
- Malware indicators (mutex names, persistence paths)
-
Threat Hunt Integration: Invoke
threat-hunteragent to find lateral movement:- Look for other systems the attacker may have reached
- Correlate IOCs across available log sources
-
Timeline Build: Write UTC-ordered timeline to
$IR_DIR/timeline/timeline.md:| UTC Timestamp | Event | Source | ATT&CK TTP | Significance | |---------------|-------|--------|------------|--------------| -
Output Deliverables:
═══ IR DELIVERABLES ════════════════════════════ immediate_actions.md — Containment steps timeline.md — UTC event timeline iocs.txt — Indicators of compromise evidence_manifest.txt — Chain of custody log ════════════════════════════════════════════════ Next: Share IOCs with security team Next: Brief stakeholders using immediate_actions.md -
Write Evidence Manifest to
$IR_DIR/evidence_manifest.txt:Chain of Custody — $ARGUMENTS — $(date -u +%Y-%m-%dT%H:%M:%SZ) Operator: $(whoami) Files collected: [list all files with sha256 hashes]
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.
- 5d ago First seen · 87 lines · 15 tokens per session scan A 57c939520338
ir is a command published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 860 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
bypass-403
Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when installed; otherwise runs a built-in matrix of 38+ techniques. Usage: /bypass-403 | /bypass-403 -l.
recon
Run the full recon pipeline by invoking tools/reconengine.sh — subdomain enum (subfinder + amass + crt.sh + wayback), httpx live host probing with tech detection, nmap port scan, gau URL collection, JS analysis, ffuf directory fuzzing, parameter discovery, config exposure check, CI/CD workflow scan. Outputs to recon/…
spray
Password spray with hard guards — typed-hostname confirmation, lockout warning, audit log. Modes: http-form (custom login page), oauth (password grant), o365 + okta (via TREVORspray). Default delay 30min/round + 60s jitter. Usage /spray --mode --users --passes.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.
autopilot
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
report
Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report.