P Code Review Security — Security agent for Claude Code
Invoked by p-code-review to run the security channel across the entire working tree (no diff).
How to install P Code Review Security
Installs to ~/.claude/agents/jayant2907-p-code-review-p-code-review-security.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Jayant2907/p-code-review/HEAD/agents/p-code-review-security.md -o ~/.claude/agents/jayant2907-p-code-review-p-code-review-security.md Restart Claude Code, or start a new session, for it to be picked up.
What P Code Review Security does
name: p-code-review-security description: Invoked by p-code-review to run the security channel across the entire working tree (no diff). Adversarial read of the codebase — untrusted-input flows, auth gaps, secret exposure, unsafe deps. Returns strict JSON. Inherits the model selected in the invoking Claude session. Not intended for standalone use — invoke the p-code-review skill instead. tools: [Read, Grep, Glob, Bash]
Security channel — codebase audit
You are one of three review cha
Alternatives in Security
- Gitnexus Security Boundary Reviewer — GitNexus security and trust-boundary reviewer 45.8k ★
- Deps Audit — You are a dependency security expert specializing in vulnerability scanning, license compliance, and 31.9k ★
- JS Analyzer — JavaScript static analysis agent for client-side security review 812 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Fallow
Run a codebase-intelligence audit (fallow) scoped to working-tree changes and report raw findings — dead code,
ForensicAgent
Forensic security analyst — PII detection, secret scanning, identity leak auditing across git history, staged
React Security
Frontend security reviewer persona for React apps. Use to review XSS risks, secret exposure in client bundles,
Security Privacy Reviewer
Reviews secrets, unsafe commands, prompt-injection vectors from sources, untrusted external data, email/deploy
Offensive Security Engineer
Red-team the verification engine. Use to hunt false SAFE verdicts, shadow-tree isolation escapes, credential l
Audit Fix Agent
Applies a single verified audit finding as a code fix in one file. Runs in parallel with sibling fix agents in
Related Skills
Package Doctor
Scan Python dependencies for exploited CVEs and abandoned packages that handle untrusted input, ranked by CISA
My Security Review
Run a personal agent-tooling security review - secrets, shell/hook command execution, untrusted input, plugin/
Review Cicd Pipeline
Audit CI/CD pipelines for missing quality gates, unpinned actions, secret exposure in logs, and deploy steps t