security-review

security-review is a command for Claude Code from CrashBytes/claude-role-skills. It costs 8 tokens per session (529 once invoked), scanned A, original, Apache-2.0.

A security-focused review of a file or code changes. It checks common application risks, including unsafe input handling, weak authentication, exposed sensitive data, access-control errors, insecure settings, and vulnerable dependencies.

In plain words
What is it for?
Use it to review a file, a Git change set, staged changes, or recent changes for vulnerabilities and missing security controls.
Why use it?
It helps find security problems before code is merged or released. It focuses review attention on risks that ordinary code review may miss, such as secret exposure, injection, and unauthorized access.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the role-based-skills plugin — 7 skills, 15 commands shipped together

Good fit Use it to review a file, a Git change set, staged changes, or recent changes for vulnerabilities and missing security controls.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/crashbytes/claude-role-skills/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/CrashBytes/claude-role-skills

Made for: Claude Code.

Or install role-based-skills, the plugin that ships this one along with the rest of its 7 skills, 15 commands.

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/crashbytes/claude-role-skills/security-review.svg)](https://agentmods.dev/commands/crashbytes/claude-role-skills/security-review)
Your own site
<a href="https://agentmods.dev/commands/crashbytes/claude-role-skills/security-review"><img src="https://agentmods.dev/badge/commands/crashbytes/claude-role-skills/security-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 529 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 $0.00008 $0.00529
Opus 5 $0.00004 $0.00264
Sonnet 5 $0.00002 $0.00106
Haiku 4.5 $0.00001 $0.00053

Measured 8d ago against content hash 3ce16620def6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

commands/security-review.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review

Perform a security-focused code review on a file or set of changes.

Arguments

Target to review: $ARGUMENTS

Context

Recent changes: !git diff --stat HEAD~1 2>/dev/null || echo "No git context"

Workflow

  1. Identify review scope

    • If a file path is provided, read it
    • If a git ref is provided, get the diff
    • If no argument, review staged or recent changes
  2. Check OWASP Top 10

    • Injection: SQL, NoSQL, OS command, LDAP injection via unsanitized inputs
    • Broken Auth: Hardcoded credentials, weak session management, missing MFA hooks
    • Sensitive Data: Secrets in code, unencrypted PII, excessive logging of sensitive data
    • XXE / Deserialization: Unsafe XML parsing, insecure deserialization
    • Broken Access Control: Missing authorization checks, IDOR vulnerabilities, path traversal
    • Misconfig: Debug mode enabled, default credentials, verbose error messages in production
    • XSS: Unescaped user input in HTML output, innerHTML usage, dangerouslySetInnerHTML
    • Insecure Dependencies: Known CVEs in dependencies (check package.json/requirements.txt)
    • Insufficient Logging: Missing audit trails for auth events and data access
    • SSRF: Unvalidated URLs in server-side requests
  3. Check secure coding patterns

    • Input validation at trust boundaries
    • Output encoding for the correct context (HTML, URL, JS, CSS)
    • Parameterized queries (no string concatenation in SQL)
    • Proper error handling (no stack traces to users)
    • Secure defaults (deny by default, least privilege)
    • Secrets management (env vars or vault, not hardcoded)
  4. Check dependency security

    • If package.json exists: npm audit findings
    • If requirements.txt exists: known vulnerabilities
    • Flag any pinned versions with known CVEs
  5. Output

    • Issues grouped by severity: Critical / High / Medium / Low / Info
    • Each issue: file, line, vulnerability type, code snippet, fix recommendation
    • Summary: total issues by severity, overall risk assessment

Read the full file on GitHub · 55 lines

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 · 55 lines · 8 tokens per session scan A 3ce16620def6

Subscribe to this mod's changes

security-review is a command published in the GitHub repository CrashBytes/claude-role-skills (6 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 529 once invoked, about $0.0000 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 2026-08-31.