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/huntgit 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/hunt)<a href="https://agentmods.dev/commands/mukul975/threatswarm/hunt"><img src="https://agentmods.dev/badge/commands/mukul975/threatswarm/hunt.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 | $0.00012 | $0.00754 |
| Opus 5 | $0.00006 | $0.00377 |
| Sonnet 5 | $0.00002 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00075 |
Grade A, and why
hunt 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 6d 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 threat hunt with hypothesis: $ARGUMENTS
Parse $ARGUMENTS for: hypothesis text, optional timeframe (e.g., "last 7 days"), affected systems.
-
Hunt Setup:
═══════════════════════════════════════════════ THREAT HUNT START Hypothesis: $ARGUMENTS Timestamp: $(date -u +%Y-%m-%dT%H:%M:%SZ) Log dir: evidence/$(date +%Y%m%d)/hunt/ ═══════════════════════════════════════════════Create:
mkdir -p evidence/$(date +%Y%m%d)/hunt/{hypotheses,queries,findings} -
Map Hypothesis to ATT&CK: Identify relevant TTPs from the hypothesis:
- PowerShell / script execution → T1059.001, T1059.003
- Lateral movement → T1021.001 (RDP), T1021.002 (SMB), T1021.006 (WinRM)
- Credential dumping → T1003.001 (LSASS), T1003.003 (NTDS)
- Persistence → T1547.001 (Run Keys), T1053.005 (Scheduled Task)
- C2 beaconing → T1071.001 (HTTP/S), T1071.004 (DNS)
- Data exfiltration → T1041 (exfil over C2), T1048 (exfil via protocol)
-
Invoke
threat-hunterAgent: Delegate with:- Full hypothesis text from $ARGUMENTS
- ATT&CK TTP mapping
- Available log sources (auth.log, syslog, nginx access, Windows Event Logs, pcaps)
- Timeframe context
-
Query Execution: The threat-hunter agent runs ATT&CK-aligned queries:
- Linux auth log pattern matching
- Web server log anomaly detection
- Network traffic analysis (if pcaps available in evidence/)
- Windows Event Log correlation (if accessible)
-
Cross-Source Correlation: Correlate findings across log sources:
- Match IP addresses across auth, web, and network logs
- Timeline reconstruction of suspicious activity
- Confidence scoring per finding
-
Write Hunt Report: Output to
evidence/$(date +%Y%m%d)/hunt/hunt_report.md:- Hypothesis tested
- Queries run with results
- Confirmed/likely/possible findings
- IOCs extracted (IPs, domains, hashes)
- Recommended follow-up hunts
-
Print Summary:
═══ HUNT RESULTS ═══════════════════ Hypothesis: [text] ATT&CK TTPs: [T1234, T1235...] Findings Confirmed: X Findings Possible: X IOCs Extracted: X Report: evidence/$(date +%Y%m%d)/hunt/hunt_report.md ════════════════════════════════════
If no evidence/ files exist and no log access is configured, output:
⚠ No log sources found. Configure log paths or run recon first.
Available: /var/log/auth.log, /var/log/nginx/access.log, pcap files in evidence/
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.
- 6d ago First seen · 70 lines · 12 tokens per session scan A a3466dbdc923
hunt is a command published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 754 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.
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.
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.
triage
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
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.
llm-redteam
LLM red-team corpus runner — fires categorized prompt-injection / jailbreak / system-prompt-leak / data-exfil / indirect-injection / guardrail-bypass payloads at a chat endpoint and canary-detects which land. Usage: /llm-redteam --url --field message [--category jailbreak].