Application Security Reviewer — Security agent for Claude Code
Read-only contextual reviewer for application-security and multitenancy practices.
How to install Application Security Reviewer
Installs to ~/.claude/agents/androsland-best-practices-application-security-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/androsland/best-practices/HEAD/agents/application-security-reviewer.md -o ~/.claude/agents/androsland-best-practices-application-security-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Application Security Reviewer does
name: application-security-reviewer description: Read-only contextual reviewer for application-security and multitenancy practices. Traces real trust and data boundaries instead of judging keywords. Never modifies files. tools: Read, Grep, Glob, Bash model: sonnet effort: medium
Read `/references/reviewer-contract.md` completely. Review every practice in the supplied `application-security` packet against `` and the shared project map.
Trace relevant request an
Alternatives in Security
- Gitnexus Security Boundary Reviewer — GitNexus security and trust-boundary reviewer 45.8k ★
- Security Architecture — Boucle implements a defense-in-depth security model to protect against prompt injection attacks and maintain t 61 ★
- Threat Modeler — Threat-modeling specialist using STRIDE, PASTA, and LINDDUN 50 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Review Spec Red Team
Security-focused adversarial reviewer for specs. Finds attack paths, bypass vectors, and failure modes the spe
Appsec AI Security Reviewer
Use for AI/LLM application security review: direct/indirect prompt injection, tool and agent authorization, RA
Security Lens
Application security lens for DevBox reviews. Threat-models a plan or diff across its trust boundaries (STRIDE
Scout Opus High
Read-only analyst for judging inside the sub-agent — root-cause analysis, a security sweep, reviewing a diff f
Example Reviewer
Independently review a specific base/head diff for correctness, regression, security, architecture boundaries,
Finding Skeptic
Read-only adversarial verifier for audit findings. Given one finding and one skeptic lens, actively tries to r
Related Skills
Security Threat Model
Generate repo-specific threat models identifying trust boundaries
Threat Model Skill
Claude Code skill: write the project's security constitution (assets, roles, trust boundaries, invariants, ent
Client Security Review
Review browser, SPA, Electron, and mobile trust boundaries: DOM, origins, IPC, navigation, storage, and server