Auto-Company: Skill for Claude Code

.claude/skills/code-review-security/SKILL.md

code-review-security is a skill for Claude Code from MaxMiksa/Auto-Company. It costs 102 tokens per session (3,677 once invoked), scanned A, original, MIT.

A security-focused code-review skill with checklists and scanning patterns. It covers pull-request reviews, authentication and authorization, input validation, and common web risks such as SQL injection, cross-site scripting, and cross-site request forgery.

In plain words
What is it for?
Reviewing pull requests, auditing access-control code, checking OWASP Top 10 risks, and validating protections such as input sanitization and CSRF tokens.
Why use it?
It helps find security weaknesses during code review and before changes are released. It provides checks for several common web-application attack patterns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is MaxMiksa/Auto-Company's own configuration. It tells Claude Code how to work on Auto-Company itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Auto-Company configures →

About the project

Auto-Company is a software system that runs a recurring team of AI agents on a personal computer, where the agents plan work, make decisions, write code, deploy applications, and handle marketing. It is intended for autonomous product development on Windows, Linux, or macOS, using command-line agent tools and a local dashboard to track cycles and results. The catalogue entries are skills, agents, settings, and instructions that support this automated workflow.

MaxMiksa/Auto-Company · 3,141 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to MaxMiksa/Auto-Company. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MaxMiksa/Auto-Company/main/.claude/skills/code-review-security/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MaxMiksa/Auto-Company

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 code-review-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/maxmiksa/auto-company/code-review-security/github.svg)](https://agentmods.dev/skills/maxmiksa/auto-company/code-review-security)
Your own site
<a href="https://agentmods.dev/skills/maxmiksa/auto-company/code-review-security"><img src="https://agentmods.dev/badge/skills/maxmiksa/auto-company/code-review-security/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 code-review-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/maxmiksa/auto-company/code-review-security"><img src="https://agentmods.dev/badge/skills/maxmiksa/auto-company/code-review-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00102 $0.03677
Opus 5.5 $0.00041 $0.01471
Sonnet 5.5 $0.00020 $0.00735
Haiku 4.5 $0.00010 $0.00368

Measured 1mo ago against content hash 6a7d57ae5b2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-review-security scanned grade A with 1 finding 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/security-scan.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(f"convert {filename}", shell=True)
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/skills/code-review-security/SKILL.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Security

When to Use

Activate this skill when:

  • Reviewing pull requests for security vulnerabilities
  • Auditing authentication or authorization code changes
  • Reviewing code that handles user input, file uploads, or external data
  • Checking for OWASP Top 10 vulnerabilities in new features
  • Validating that secrets are not committed to the repository
  • Scanning dependencies for known vulnerabilities
  • Reviewing API endpoints that expose sensitive data

Output: Write findings to security-review.md with severity, file:line, description, and recommendations.

Do NOT use this skill for:

  • Deployment infrastructure security (use docker-best-practices)
  • Incident response procedures (use incident-response)
  • General code quality review without security focus (use pre-merge-checklist)
  • Writing implementation code (use python-backend-expert or react-frontend-expert)

Instructions

OWASP Top 10 Checklist

Review every PR against the OWASP Top 10 (2021 edition). Each category below includes specific checks for Python/FastAPI and React codebases.


A01: Broken Access Control

What to look for:

  • Missing authorization checks on endpoints
  • Direct object reference without ownership verification
  • Endpoints that expose data without role-based filtering
  • Missing Depends() for auth on new routes

Python/FastAPI checks:

# BAD: No authorization check -- any authenticated user can access any user
@router.get("/users/{user_id}")
async def get_user(user_id: int, db: Session = Depends(get_db)):
    return await user_repo.get(user_id)

# GOOD: Verify the requesting user owns the resource or is admin
@router.get("/users/{user_id}")
async def get_user(
    user_id: int,
    current_user: User = Depends(get_current_user),
    db: Session = Depends(get_db),
):
    if current_user.id != user_id and current_user.role != "admin":
        raise HTTPException(status_code=403, detail="Forbidden")
    return await user_repo.get(user_id)

Read the full file on GitHub · 486 lines

Files

What ships with it

1 file 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. 1mo ago First seen · 486 lines · 102 tokens per session scan A 6a7d57ae5b2f

Subscribe to this mod's changes

code-review-security is a skill published in the GitHub repository MaxMiksa/Auto-Company (3,141 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 3,677 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.