
Security reasoning
MANDATORY threat analysis
- Scripts
- None
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 28
- Last commit
- 4 months ago
- License
- MIT
- Listing updated
- today
When your agent uses it
MANDATORY threat analysis. You MUST invoke this skill before writing or approving ANY code involving authentication, authorization, cryptography, input handling, payment processing, PII, secrets management, API endpoints, or trust boundaries. Do NOT write security-sensitive code without running STRIDE analysis first. Do NOT say you will add security later. Auth is a design decision, not a feature to bolt on.
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
From a static check of its 1 file (4 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Install
This skill ships in the praxis plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):
/plugin marketplace add xD4O/praxis
/plugin install praxis@praxisOr copy only this skill to ~/.claude/skills/security-reasoning:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xD4O/praxis.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/security-reasoning &&
cp -R "$tmp/skills/security-reasoning" ~/.claude/skills/security-reasoning &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/security-reasoning inside it instead.
Copy the skill folder to ~/.agents/skills/security-reasoning to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xD4O/praxis.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/security-reasoning &&
cp -R "$tmp/skills/security-reasoning" ~/.agents/skills/security-reasoning &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/security-reasoning inside it instead.
Copy the skill folder to ~/.cursor/skills/security-reasoning to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xD4O/praxis.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/security-reasoning &&
cp -R "$tmp/skills/security-reasoning" ~/.cursor/skills/security-reasoning &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/security-reasoning inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/xD4O/praxis.git --path skills/security-reasoningOr copy the folder to ~/.gemini/skills/security-reasoning yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/security-reasoning:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/xD4O/praxis.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/security-reasoning &&
cp -R "$tmp/skills/security-reasoning" ~/.copilot/skills/security-reasoning &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/security-reasoning inside it instead.
Get the folder:
git clone --depth 1 https://github.com/xD4O/praxis.gitThen copy praxis/skills/security-reasoning into your agent's skills folder as security-reasoning. Agents that support SKILL.md read one folder per skill.
Security reasoning FAQ
How do I install Security reasoning in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/security-reasoning to use it in all your projects, or to .claude/skills/security-reasoning in one project. Or install the praxis plugin, which includes it: /plugin marketplace add xD4O/praxis, then /plugin install praxis@praxis.
Does Security reasoning run scripts?
No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Security reasoning?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
What are the best alternatives to Security reasoning?
The closest alternatives to Security reasoning are Audit integrity, Tm7 threat model, MCP implementation security review, Threat model analyst and Security review.
More from xD4O/praxis
Alternatives to Security reasoning

Audit integrity
SkillEnforce output quality, evidence verification, and quality gates across security audits
- Open source
- 41.3K GitHub stars
- Security

Tm7 threat model
SkillCreates valid Microsoft Threat Modeling Tool (.tm7) files compatible with the Microsoft Threat Modeling Tool v7.3+
- Open source
- 41.3K GitHub stars
- Security

Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — auth
- Open source
- 41.3K GitHub stars
- Security

Threat model analyst
SkillFull STRIDE-A threat model analysis and incremental update skill for repositories and systems
- Open source
- 41.3K GitHub stars
- Security

Security review
SkillAI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component intera
- Open source
- 41.3K GitHub stars
- Security

Spring security
SkillConfigure, test and review Spring Security 6/7 in Spring Boot 3/4 apps: SecurityFilterChain lambda DSL, method security, OAuth2 resource ser
- Open source
- 41.3K GitHub stars
- Security



