obra/
superpowers
obra/superpowersSkills
An agentic skills framework & software development methodology that works.
285k
1 add
Claude Code skills for application security checks
This repository is a plugin marketplace for Ghost Security’s Claude Code skills. It packages AppSec workflows for building repository context, scanning dependencies and secrets, checking code, validating findings against a live app, and producing a combined report.
405 stars•26 forks•Python•Updated 14d ago
Who it's for
Builders who use Claude Code and want application security skills they can install once and reuse.
What it delivers
You can run security-focused agent workflows without rebuilding the same scan and review steps each time.
What it does
Repository context skill
Builds shared context for a codebase, including business criticality, sensitive data, and component map.
Dependency scan skill
Assesses dependency vulnerabilities for exploitability.
Secret scan skill
Reviews detected secrets and credentials in context.
Code scan skill
Finds code security issues with AI-assisted analysis.
Validation and reporting skills
Validates findings against a live application, proxies traffic for validation, and combines results into one report.
How to get it
- 1With Claude Code
claude plugin marketplace add ghostsecurity/skills claude plugin install ghost@ghost-security claude
- 2Alternatively, install the skills plugin within Claude Code
/plugin marketplace add ghostsecurity/skills /plugin install ghost@ghost-security
README
Ghost Security Skills/Plugin Marketplace
Plugin marketplace repository for Ghost Security's AI-native application security skills for Claude Code.
Quick Installation
With Claude Code:
claude plugin marketplace add ghostsecurity/skills
claude plugin install ghost@ghost-security
claude
Alternatively, install the skills plugin within Claude Code:
/plugin marketplace add ghostsecurity/skills
/plugin install ghost@ghost-security
Currently, you will need to restart Claude Code for the plugin to load.
Comprehensive Documentation
Full documentation, tutorials, and video guides at ghostsecurity.ai.
Skills in this Repository Marketplace
| Skill | Description |
|---|---|
ghost-repo-context | Build shared repository context (business criticality, sensitive data, component map) |
ghost-scan-deps | Exploitability analysis of dependency vulnerabilities (SCA) |
ghost-scan-secrets | Context assessment of detected secrets and credentials |
ghost-scan-code | AI-powered detection of code security issues (SAST) |
ghost-report | Combined security report across all scan results |
ghost-validate | Dynamic validation of findings against a live application (DAST) |
ghost-proxy | HTTP proxy for the ghost-validate skill |
ghost-exo | Build, improve, and debug workflows on the exo agent orchestration platform |
ghost-repo-context
ghost-scan-code
ghost-scan-deps
ghost-scan-secrets
ghost-validate
ghost-report
Contributions, Feedback, Feature Requests, and Issues
Open an Issue per the Contributing guidelines and Code of Conduct
License
This repository is licensed under the Apache License 2.0. See LICENSE for details.
Files in the repo
Repository payload•6 top-level entries
- .claude-plugin
- .github
- plugins
- .gitignore
- LICENSE
- README.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More skills
addyosmani/agent-skillsSkills
Production-grade engineering skills for AI coding agents.
93k
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
33k
Da7-Tech/
SureForge
Da7-Tech/SureForgeSkills
Agent Skill for complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before calling it done. Plain text, no runtime.
84
Leonxlnx/
unlazy
Leonxlnx/unlazySkills
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
3.2k
internet-court/
internet-court-skill
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.
5.5k