security-review

security-review is a command for Claude Code from Security-Phoenix-demo/security-skills-claude-code. It costs 30 tokens per session (541 once invoked), scanned A, original, MIT.

A security-review command for recent code changes that routes the work to a multi-language reviewer when available. It checks authentication, output encoding, network requests, secrets, input, configuration, dependencies, and failure handling.

In plain words
What is it for?
Use it on recent changes or a specified path, security topic, or vulnerability category; it returns findings with evidence and suggested fixes.
Why use it?
It helps find confirmed security problems before a pull request or release while keeping the review focused on relevant changes.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it on recent changes or a specified path, security topic, or vulnerability category; it returns findings with evidence and suggested fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/security-phoenix-demo/security-skills-claude-code/security-review
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.

Clone the repo
git clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-code

Made for: Claude Code.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/security-phoenix-demo/security-skills-claude-code/security-review.svg)](https://agentmods.dev/commands/security-phoenix-demo/security-skills-claude-code/security-review)
Your own site
<a href="https://agentmods.dev/commands/security-phoenix-demo/security-skills-claude-code/security-review"><img src="https://agentmods.dev/badge/commands/security-phoenix-demo/security-skills-claude-code/security-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 541 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 $0.00030 $0.00541
Opus 5 $0.00015 $0.00270
Sonnet 5 $0.00006 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured 8d ago against content hash 172c7e202e7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

security-review 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 8d 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.

skills/Security Assessment/install/commands/security-review.md · 39 lines

What it actually says

You are running the security-reviewer skill against recent changes.

Skill

Load skills/Security Assessment/Security-automated-claude-skills/.claude/skills/security-reviewer/SKILL.md — multi-language reviewer (Python, JS/TS, Go, Java/Kotlin, Rust, Ruby, .NET) with per-language reference packs in languages/, OWASP/ASVS + endpoint checklists in checklists/, and a triage playbook in playbooks/.

Instructions

  1. Load the skill above. Read it fully, including the language reference(s) matching the project's stack and the relevant checklists.
  2. Determine scope:
    • If $ARGUMENTS is provided, scope to that (path, keyword like auth/endpoints/frontend, or category).
    • Otherwise, scope to files changed since the last commit (git diff --name-only HEAD~1) plus obviously security-relevant globs (route files, middleware, auth, templates, IaC).
  3. Apply the 8-point check (Authn/Authz, Output encoding, SSRF, Secrets, Input handling, Config & headers, Supply chain, Failure modes).
  4. Confirm before flagging. Pattern matches that turn out safe-by-context get dropped. Open the file and read enough surrounding context to confirm.
  5. Output one block per finding in the skill's output format:
    [SEVERITY] <one-line summary>
    File:     <path>:<line>
    Category: <one of the 8 categories>
    Evidence: <code snippet or pattern matched>
    Fix:      <concrete change, ideally a diff>
    Refs:     <CWE-XXX, OWASP A0X:2021, ASVS V-X.Y.Z>
    
  6. If nothing fires, say so explicitly and list residual risks or untested areas — silence is not a clean bill.

Scope guard

  • Read-only. Do not edit code as part of the review itself; describe fixes precisely instead.
  • For diff-level checks against a base ref, prefer /security-0day.
  • For pre-release sweeps, prefer /security-assessment.
  • For architecture / new feature design, prefer /threatmodel.
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. 8d ago First seen · 39 lines · 30 tokens per session scan A 172c7e202e7f

Subscribe to this mod's changes

security-review is a command published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (69 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 541 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 2026-08-30.