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/zsutxz/claudelearning/security-dependenciesgit clone --depth 1 https://github.com/zsutxz/ClaudeLearningWrote 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/zsutxz/claudelearning/security-dependencies)<a href="https://agentmods.dev/commands/zsutxz/claudelearning/security-dependencies"><img src="https://agentmods.dev/badge/commands/zsutxz/claudelearning/security-dependencies.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 | $0.00000 | $0.03602 |
| Opus 5 | $0.00000 | $0.01801 |
| Sonnet 5 | $0.00000 | $0.00720 |
| Haiku 4.5 | $0.00000 | $0.00360 |
Grade A, and why
security-dependencies 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
npm_result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Vulnerability Scanning
You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and supply chain security. Scan project dependencies across multiple ecosystems to identify vulnerabilities, assess risks, and provide automated remediation strategies.
Context
The user needs comprehensive dependency security analysis to identify vulnerable packages, outdated dependencies, and license compliance issues. Focus on multi-ecosystem support, vulnerability database integration, SBOM generation, and automated remediation using modern 2024/2025 tools.
Requirements
$ARGUMENTS
Instructions
1. Multi-Ecosystem Dependency Scanner
import subprocess
import json
import requests
from pathlib import Path
from typing import Dict, List, Any
from dataclasses import dataclass
from datetime import datetime
@dataclass
class Vulnerability:
package: str
version: str
vulnerability_id: str
severity: str
cve: List[str]
cvss_score: float
fixed_versions: List[str]
source: str
class DependencyScanner:
def __init__(self, project_path: str):
self.project_path = Path(project_path)
self.ecosystem_scanners = {
'npm': self.scan_npm,
'pip': self.scan_python,
'go': self.scan_go,
'cargo': self.scan_rust
}
def detect_ecosystems(self) -> List[str]:
ecosystem_files = {
'npm': ['package.json', 'package-lock.json'],
'pip': ['requirements.txt', 'pyproject.toml'],
'go': ['go.mod'],
'cargo': ['Cargo.toml']
}
detected = []
for ecosystem, patterns in ecosystem_files.items():
if any(list(self.project_path.glob(f"**/{p}")) for p in patterns):
detected.append(ecosystem)
return detected
def scan_all_dependencies(self) -> Dict[str, Any]:
ecosystems = self.detect_ecosystems()
results = {
'timestamp': datetime.now().isoformat(),
'ecosystems': {},
'vulnerabilities': [],
'summary': {
'total_vulnerabilities': 0,
'critical': 0,
'high': 0,
'medium': 0,
'low': 0
}
}
for ecosystem in ecosystems:
scanner = self.ecosystem_scanners.get(ecosystem)
if scanner:
ecosystem_results = scanner()
results['ecosystems'][ecosystem] = ecosystem_results
results['vulnerabilities'].extend(ecosystem_results.get('vulnerabilities', []))
self._update_summary(results)
results['remediation_plan'] = self.generate_remediation_plan(results['vulnerabilities'])
results['sbom'] = self.generate_sbom(results['ecosystems'])
return results
def scan_npm(self) -> Dict[str, Any]:
results = {
'ecosystem': 'npm',
'vulnerabilities': []
}
try:
npm_result = subprocess.run(
['npm', 'audit', '--json'],
cwd=self.project_path,
capture_output=True,
text=True,
timeout=120
)
if npm_result.stdout:
audit_data = json.loads(npm_result.stdout)
for vuln_id, vuln in audit_data.get('vulnerabilities', {}).items():
results['vulnerabilities'].append({
'package': vuln.get('name', vuln_id),
'version': vuln.get('range', ''),
'vulnerability_id': vuln_id,
'severity': vuln.get('severity', 'UNKNOWN').upper(),
'cve': vuln.get('cves', []),
'fixed_in': vuln.get('fixAvailable', {}).get('version', 'N/A'),
'source': 'npm_audit'
})
except Exception as e:
results['error'] = str(e)
return results
def scan_python(self) -> Dict[str, Any]:
results = {
'ecosystem': 'python',
'vulnerabilities': []
}
try:
safety_result = subprocess.run(
['safety', 'check', '--json'],
cwd=self.project_path,
capture_output=True,
text=True,
timeout=120
)
if safety_result.stdout:
safety_data = json.loads(safety_result.stdout)
for vuln in safety_data:
results['vulnerabilities'].append({
'package': vuln.get('package_name', ''),
'version': vuln.get('analyzed_version', ''),
'vulnerability_id': vuln.get('vulnerability_id', ''),
'severity': 'HIGH',
'fixed_in': vuln.get('fixed_version', ''),
'source': 'safety'
})
except Exception as e:
results['error'] = str(e)
return results
def scan_go(self) -> Dict[str, Any]:
results = {
'ecosystem': 'go',
'vulnerabilities': []
}
try:
govuln_result = subprocess.run(
['govulncheck', '-json', './...'],
cwd=self.project_path,
capture_output=True,
text=True,
timeout=180
)
if govuln_result.stdout:
for line in govuln_result.stdout.strip().split('\n'):
if line:
vuln_data = json.loads(line)
if vuln_data.get('finding'):
finding = vuln_data['finding']
results['vulnerabilities'].append({
'package': finding.get('osv', ''),
'vulnerability_id': finding.get('osv', ''),
'severity': 'HIGH',
'source': 'govulncheck'
})
except Exception as e:
results['error'] = str(e)
return results
def scan_rust(self) -> Dict[str, Any]:
results = {
'ecosystem': 'rust',
'vulnerabilities': []
}
try:
audit_result = subprocess.run(
['cargo', 'audit', '--json'],
cwd=self.project_path,
capture_output=True,
text=True,
timeout=120
)
if audit_result.stdout:
audit_data = json.loads(audit_result.stdout)
for vuln in audit_data.get('vulnerabilities', {}).get('list', []):
advisory = vuln.get('advisory', {})
results['vulnerabilities'].append({
'package': vuln.get('package', {}).get('name', ''),
'version': vuln.get('package', {}).get('version', ''),
'vulnerability_id': advisory.get('id', ''),
'severity': 'HIGH',
'source': 'cargo_audit'
})
except Exception as e:
results['error'] = str(e)
return results
def _update_summary(self, results: Dict[str, Any]):
vulnerabilities = results['vulnerabilities']
results['summary']['total_vulnerabilities'] = len(vulnerabilities)
for vuln in vulnerabilities:
severity = vuln.get('severity', '').upper()
if severity == 'CRITICAL':
results['summary']['critical'] += 1
elif severity == 'HIGH':
results['summary']['high'] += 1
elif severity == 'MEDIUM':
results['summary']['medium'] += 1
elif severity == 'LOW':
results['summary']['low'] += 1
def generate_remediation_plan(self, vulnerabilities: List[Dict]) -> Dict[str, Any]:
plan = {
'immediate_actions': [],
'short_term': [],
'automation_scripts': {}
}
critical_high = [v for v in vulnerabilities if v.get('severity', '').upper() in ['CRITICAL', 'HIGH']]
for vuln in critical_high[:20]:
plan['immediate_actions'].append({
'package': vuln.get('package', ''),
'current_version': vuln.get('version', ''),
'fixed_version': vuln.get('fixed_in', 'latest'),
'severity': vuln.get('severity', ''),
'priority': 1
})
plan['automation_scripts'] = {
'npm_fix': 'npm audit fix && npm update',
'pip_fix': 'pip-audit --fix && safety check',
'go_fix': 'go get -u ./... && go mod tidy',
'cargo_fix': 'cargo update && cargo audit'
}
return plan
def generate_sbom(self, ecosystems: Dict[str, Any]) -> Dict[str, Any]:
sbom = {
'bomFormat': 'CycloneDX',
'specVersion': '1.5',
'version': 1,
'metadata': {
'timestamp': datetime.now().isoformat()
},
'components': []
}
for ecosystem_name, ecosystem_data in ecosystems.items():
for vuln in ecosystem_data.get('vulnerabilities', []):
sbom['components'].append({
'type': 'library',
'name': vuln.get('package', ''),
'version': vuln.get('version', ''),
'purl': f"pkg:{ecosystem_name}/{vuln.get('package', '')}@{vuln.get('version', '')}"
})
return sbom
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 · 523 lines · 0 tokens per session scan A df3f11aa01d2
security-dependencies is a command published in the GitHub repository zsutxz/ClaudeLearning (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,602 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.