secdevai-review

secdevai-review is a skill for Claude Code from RedHatProductSecurity/prodsec-skills. It costs 58 tokens per session (1,347 once invoked), scanned A, original, Apache-2.0.

A security code-review skill that checks source files, commits, or whole codebases for common security weaknesses using established OWASP, CWE/SANS, and testing guidance.

In plain words
What is it for?
It is for reviewing files, commits, or repositories and scanning for issues such as those in the OWASP Top 10 and CWE/SANS Top 25.
Why use it?
It helps find security problems before code is merged or released, across different programming languages and frameworks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the prodsec-skills plugin — 133 skills shipped together

Good fit It is for reviewing files, commits, or repositories and scanning for issues such as those in the OWASP Top 10 and CWE/SANS Top 25.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhatproductsecurity/prodsec-skills/secdevai-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.

Any agent
npx skills add RedHatProductSecurity/prodsec-skills --skill secdevai-review
Clone the repo
git clone --depth 1 https://github.com/RedHatProductSecurity/prodsec-skills

Made for: Claude Code.

Or install prodsec-skills, the plugin that ships this one along with the rest of its 133 skills.

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 secdevai-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/secdevai-review/github.svg)](https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/secdevai-review)
Your own site
<a href="https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/secdevai-review"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/secdevai-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for secdevai-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/secdevai-review"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/secdevai-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,347 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 $0.00058 $0.01347
Opus 5 $0.00029 $0.00674
Sonnet 5 $0.00012 $0.00269
Haiku 4.5 $0.00006 $0.00135

Measured 9d ago against content hash d73a8a1bd346, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

secdevai-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 9d 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.

experimental/secdevai-review/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Code Review

AI-powered security review of source code using OWASP Top 10, CWE/SANS Top 25, and OWASP WSTG patterns. Supports file review, commit review, and full codebase scan modes across all major languages.

When to Use This Skill

  • Reviewing source code files or directories for security vulnerabilities
  • Reviewing one or more git commits for security-relevant changes
  • Scanning an entire codebase for OWASP Top 10 / CWE/SANS Top 25 issues
  • Performing a security review pass before submitting a pull request

Workflow

Step 1: Determine Scope

Choose what to review (in priority order):

  1. If a specific number of recent commits is requested: review those commits
  2. If the last commit is requested: review the most recent commit
  3. If a specific file or directory is specified: review it
  4. Otherwise: scan the entire codebase

Step 2: Apply Ignore Patterns

Before scanning, exclude:

  • Binary and media files (images, fonts, compiled artifacts, archives)
  • Generated code and build output (dist/, build/, *.pyc, *.class)
  • Dependency trees (node_modules/, venv/, __pycache__/)
  • IDE and OS metadata (.vscode/, .idea/, .DS_Store)

Note: documentation files (markdown, RST, plaintext) are not excluded — they can contain hardcoded secrets, leaked infrastructure details, or AI agent instructions.

If all files are excluded, report that no security-relevant content was found. If some files are excluded, proceed with the remaining files and list the skipped files at the end of the review.

Step 3: Load Security Context

Load context based on what is being reviewed:

  • Always: Apply OWASP Top 10 (2021) patterns from ./reference/security-review.context

  • For web applications or services: Additionally apply OWASP WSTG v4.2 patterns from ./reference/wstg-testing.context

  • For Go code (.go files or go.mod present): Additionally apply Go security patterns from ./reference/golang-security.context

  • For native/systems code (C, C++, Rust, or build files such as Makefile, CMakeLists.txt, Cargo.toml): Additionally apply CWE/SANS Top 25 patterns

Read the full file on GitHub · 153 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 153 lines · 58 tokens per session scan A d73a8a1bd346

Subscribe to this mod's changes

secdevai-review is a skill published in the GitHub repository RedHatProductSecurity/prodsec-skills (52 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,347 once invoked, about $0.0003 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.