Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/patricio0312rev/skillsetnpx agentmods add skills/patricio0312rev/skillset/dependency-vulnerability-triageWrote 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/skills/patricio0312rev/skillset/dependency-vulnerability-triage)<a href="https://agentmods.dev/skills/patricio0312rev/skillset/dependency-vulnerability-triage"><img src="https://agentmods.dev/badge/skills/patricio0312rev/skillset/dependency-vulnerability-triage/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/skills/patricio0312rev/skillset/dependency-vulnerability-triage"><img src="https://agentmods.dev/badge/skills/patricio0312rev/skillset/dependency-vulnerability-triage.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 | $0.00055 | $0.03253 |
| Opus 5 | $0.00028 | $0.01626 |
| Sonnet 5 | $0.00011 | $0.00651 |
| Haiku 4.5 | $0.00006 | $0.00325 |
Grade A, and why
dependency-vulnerability-triage 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 9d 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.
import { execSync } from "child_process"; This is a copy
100% identical to dependency-vulnerability-triage — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Vulnerability Triage
Convert vulnerability reports into actionable patch plans.
Vulnerability Severity Matrix
// severity-matrix.ts
export interface Vulnerability {
id: string;
package: string;
currentVersion: string;
patchedVersion: string;
severity: "critical" | "high" | "medium" | "low";
cvss: number;
cwe: string[];
exploitability: "high" | "medium" | "low";
impact: string;
path: string[];
}
export interface PatchPriority {
vulnerability: Vulnerability;
priority: 1 | 2 | 3 | 4;
reasoning: string;
patchWindow: "24h" | "1week" | "1month" | "next-release";
breakingChange: boolean;
testingRequired: "minimal" | "moderate" | "extensive";
}
export function calculatePriority(vuln: Vulnerability): PatchPriority {
let priority: 1 | 2 | 3 | 4 = 4;
let patchWindow: "24h" | "1week" | "1month" | "next-release" = "next-release";
let testingRequired: "minimal" | "moderate" | "extensive" = "minimal";
// P1: Critical + High Exploitability + Production
if (
vuln.severity === "critical" &&
vuln.exploitability === "high" &&
isProductionDependency(vuln.package)
) {
priority = 1;
patchWindow = "24h";
testingRequired = "moderate";
}
// P2: High + Medium/High Exploitability
else if (
vuln.severity === "high" &&
["high", "medium"].includes(vuln.exploitability)
) {
priority = 2;
patchWindow = "1week";
testingRequired = "moderate";
}
// P3: Medium or Low Exploitability High
else if (
vuln.severity === "medium" ||
(vuln.severity === "high" && vuln.exploitability === "low")
) {
priority = 3;
patchWindow = "1month";
testingRequired = "minimal";
}
return {
vulnerability: vuln,
priority,
reasoning: `${vuln.severity} severity, ${vuln.exploitability} exploitability`,
patchWindow,
breakingChange: isBreakingChange(vuln.currentVersion, vuln.patchedVersion),
testingRequired,
};
}
Audit Report Parser
// scripts/parse-audit.ts
import { execSync } from "child_process";
interface NpmAuditResult {
vulnerabilities: Record<string, any>;
metadata: {
vulnerabilities: {
critical: number;
high: number;
moderate: number;
low: number;
};
};
}
function parseNpmAudit(): Vulnerability[] {
const auditOutput = execSync("npm audit --json", { encoding: "utf-8" });
const audit: NpmAuditResult = JSON.parse(auditOutput);
const vulnerabilities: Vulnerability[] = [];
Object.entries(audit.vulnerabilities).forEach(([pkg, data]) => {
vulnerabilities.push({
id: data.via[0]?.url || `vuln-${pkg}`,
package: pkg,
currentVersion: data.range,
patchedVersion: data.fixAvailable?.version || "N/A",
severity: data.severity,
cvss: data.via[0]?.cvss?.score || 0,
cwe: data.via[0]?.cwe || [],
exploitability: determineExploitability(data),
impact: data.via[0]?.title || "Unknown",
path: data.via.map((v: any) => v.name),
});
});
return vulnerabilities;
}
function determineExploitability(data: any): "high" | "medium" | "low" {
// Check if actively exploited
if (
data.via[0]?.findings?.some((f: any) => f.exploit === "proof-of-concept")
) {
return "high";
}
// Check CVSS exploitability subscore
const exploitScore = data.via[0]?.cvss?.exploitabilityScore;
if (exploitScore > 3.5) return "high";
if (exploitScore > 2.0) return "medium";
return "low";
}
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.
- 9d ago First seen · 496 lines · 55 tokens per session scan A 26a8027ae95c
dependency-vulnerability-triage is a skill published in the GitHub repository patricio0312rev/skillset (6 stars, last pushed 8mo ago), licensed MIT. It adds 55 tokens to every session and 3,253 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to dependency-vulnerability-triage, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…