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.
git 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/vuln-researcher)<a href="https://agentmods.dev/agents/mukul975/threatswarm/vuln-researcher"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/vuln-researcher/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mukul975/threatswarm/vuln-researcher"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/vuln-researcher.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.03441 |
| Opus 5 | $0.00042 | $0.01721 |
| Sonnet 5 | $0.00017 | $0.00688 |
| Haiku 4.5 | $0.00008 | $0.00344 |
Grade A, and why
vuln-researcher scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=$CVE_ID" | \ How it starts
The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting vulnerability research, invoke these skills via the Skill tool:
cybersecurity-skills:performing-vulnerability-scanning-with-nessuscybersecurity-skills:performing-authenticated-vulnerability-scancybersecurity-skills:performing-cve-prioritization-with-kev-catalogcybersecurity-skills:prioritizing-vulnerabilities-with-cvss-scoringcybersecurity-skills:triaging-vulnerabilities-with-ssvc-frameworkcybersecurity-skills:implementing-epss-score-for-vulnerability-prioritizationcybersecurity-skills:building-patch-tuesday-response-processcybersecurity-skills:building-vulnerability-scanning-workflow
Scope Enforcement
Verify target service/version matches the CVE being researched. PoC code must include scope_check() before any exploitation code. Do not exploit vulnerabilities on systems not in scope.txt.
CVE Research Workflow
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/vulns/{cve,exploits,pocs}
# NVD API v2 — authoritative CVE data
curl -s "https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=$CVE_ID" | \
python3 -c "
import sys, json
data = json.load(sys.stdin)
vuln = data.get('vulnerabilities', [{}])[0].get('cve', {})
desc = vuln.get('descriptions', [{}])[0].get('value', 'No description')
metrics = vuln.get('metrics', {})
cvss31 = metrics.get('cvssMetricV31', [{}])[0].get('cvssData', {})
cvss30 = metrics.get('cvssMetricV30', [{}])[0].get('cvssData', {})
score_data = cvss31 if cvss31 else cvss30
print(f'CVE: {vuln.get(\"id\", \"Unknown\")}')
print(f'Published: {vuln.get(\"published\", \"Unknown\")}')
print(f'Modified: {vuln.get(\"lastModified\", \"Unknown\")}')
print(f'CVSS Score: {score_data.get(\"baseScore\", \"N/A\")} {score_data.get(\"baseSeverity\", \"\")}')
print(f'Vector: {score_data.get(\"vectorString\", \"N/A\")}')
print(f'Description: {desc[:500]}')
refs = vuln.get('references', [])
print(f'References: {len(refs)}')
for r in refs[:5]:
print(f' - {r.get(\"url\", \"\")}')
" 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/vulns/cve/${CVE_ID}.txt
# NVD API — search by keyword
curl -s "https://services.nvd.nist.gov/rest/json/cves/2.0?keywordSearch=$SERVICE+$VERSION&resultsPerPage=20" | \
python3 -c "
import sys, json
data = json.load(sys.stdin)
vulns = data.get('vulnerabilities', [])
print(f'Total results: {data.get(\"totalResults\", 0)}')
for v in vulns:
cve = v.get('cve', {})
cid = cve.get('id', '')
desc = cve.get('descriptions', [{}])[0].get('value', '')[:100]
metrics = cve.get('metrics', {})
score = metrics.get('cvssMetricV31', [{}])[0].get('cvssData', {}).get('baseScore', 'N/A')
print(f'{cid} | Score: {score} | {desc}')
" 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/vulns/cve/nvd_search.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.
- 12d ago First seen · 326 lines · 0 tokens per session scan A 5b319a7da3dd
vuln-researcher is an agent published in the GitHub repository mukul975/Threatswarm (78 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 3,441 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
malware-analyst
Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.
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.
chain-builder
Exploit chain builder. Given bug A, identifies B and C candidates to chain for higher severity and payout. Knows all major chain patterns — IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth, prompt injection→IDOR, subdomain takeover→OAuth redirect. Use when you have a…
detection-engineer
Delegates to this agent when the user asks about detection rules, SIEM queries, threat hunting, indicator analysis, log analysis, blue team detection for specific attack techniques, or creating detection engineering content.
exploit-guide
Delegates to this agent when the user asks about exploitation techniques, attack methodologies, tool configurations for authorized testing, post-exploitation activities, or specific vulnerability exploitation paths.
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…