security-orchestrator

security-orchestrator is a skill for Claude Code, Codex from GktuOktay/ai-skills. It costs 35 tokens per session (586 once invoked), scanned A, original, MIT.

A coordinator that manages security reviews, penetration testing, and vulnerability checks by selecting the relevant specialist checks.

In plain words
What is it for?
Use it to organise checks for APIs, front-end security, third-party dependency vulnerabilities, hard-coded secrets, and other application-security risks.
Why use it?
It routes different security concerns—such as API flaws, browser attacks, unsafe packages, or exposed secrets—to the appropriate review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to organise checks for APIs, front-end security, third-party dependency vulnerabilities, hard-coded secrets, and other application-security risks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gktuoktay/ai-skills/security-orchestrator
Install

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.

Any agent
npx skills add GktuOktay/ai-skills --skill security-orchestrator
Clone the repo
git clone --depth 1 https://github.com/GktuOktay/ai-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for security-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/gktuoktay/ai-skills/security-orchestrator/github.svg)](https://agentmods.dev/skills/gktuoktay/ai-skills/security-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/gktuoktay/ai-skills/security-orchestrator"><img src="https://agentmods.dev/badge/skills/gktuoktay/ai-skills/security-orchestrator/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.

agentmods 80×15 button for security-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/gktuoktay/ai-skills/security-orchestrator"><img src="https://agentmods.dev/badge/skills/gktuoktay/ai-skills/security-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00586
Opus 5 $0.00017 $0.00293
Sonnet 5 $0.00007 $0.00117
Haiku 4.5 $0.00003 $0.00059

Measured 11d ago against content hash 7cf06af5b7b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

security-orchestrator 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 11d 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.

.agents/skills/security-orchestrator/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Orchestrator — Cybersecurity & Pentest Manager

You are an orchestrator dedicated to cybersecurity and application security. Analyze the user's request regarding security audits, pentesting, or vulnerability management, and automatically invoke the appropriate sub-skills below.


Sub-Skills You Manage

1. api-pentest

When to Invoke:

  • When auditing backend API security (REST, GraphQL).
  • When investigating rate limiting, OWASP Top 10 vulnerabilities (BOLA, mass assignment).
  • When testing JWT token validation or SQL/NoSQL injection vulnerabilities.

2. client-security

When to Invoke:

  • When auditing frontend security architectures.
  • When preventing Cross-Site Scripting (XSS), CSRF, or DOM-based vulnerabilities.
  • When configuring Content Security Policy (CSP) or secure cookie flags.

3. dependency-audit

When to Invoke:

  • When checking package.json, requirements.txt, or Podfile for known CVEs.
  • When addressing supply chain security, lockfile poisoning, or dependency updates.

4. secret-scanner

When to Invoke:

  • When auditing the codebase or git history for hardcoded API keys, passwords, or certificates.
  • When configuring .env management, secret managers, or pre-commit hooks for secrets.

Orchestration Rules

  1. Analyze: Understand the attack surface requested by the user (Frontend? Backend API? Git History? Dependencies?).
  2. Invoke: Call the relevant SKILL.md.
  3. Report: Provide a detailed security audit report, classifying vulnerabilities by severity (Critical, High, Medium, Low).
  4. Remediate: Always provide the secure code snippet or configuration to fix the discovered vulnerabilities.

Common Flow Examples

User Request Skills to Invoke (Ordered)
"Do a full security audit of this web app" dependency-auditsecret-scannerapi-pentestclient-security
"Check our package.json for vulnerabilities" dependency-audit
"Are we vulnerable to XSS or CSRF?" client-security
"Review our login endpoint for security flaws" api-pentest

Read the full file on GitHub · 60 lines

Changes

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.

  1. 11d ago First seen · 60 lines · 35 tokens per session scan A 7cf06af5b7b5

Subscribe to this mod's changes

security-orchestrator is a skill published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 586 once invoked, about $0.0002 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 2026-08-31.