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.
npx skills add mickeyyaya/refactoring-skills --skill security-patterns-code-reviewgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote 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.
[](https://agentmods.dev/skills/mickeyyaya/refactoring-skills/security-patterns-code-review)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/security-patterns-code-review"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/security-patterns-code-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.
<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/security-patterns-code-review"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/security-patterns-code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.02641 |
| Opus 5 | $0.00040 | $0.01321 |
| Sonnet 5 | $0.00016 | $0.00528 |
| Haiku 4.5 | $0.00008 | $0.00264 |
Grade A, and why
security-patterns-code-review 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Red Flags:** String concatenation in SQL; `exec`/`subprocess.call(shell=True)` with user values; ORM raw queries unparameterized. How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Patterns for Code Review
Overview
Security vulnerabilities are cheapest to fix at code review. Use this guide during PR review to catch OWASP Top 10 risks before they ship.
When to use: PRs touching authentication, data access, user input, external APIs, or configuration.
Quick Reference
| Area | Severity | Primary Red Flag |
|---|---|---|
| Injection (SQL/Command/LDAP) | Critical | String concatenation in queries, exec/eval with user input |
| Broken Authentication | Critical | Plaintext passwords, hardcoded secrets, JWT without expiry |
| Sensitive Data Exposure | High | Logging PII, HTTP endpoints, secrets in source code |
| XML External Entities | High | XML parsing without DTD disabled |
| Broken Access Control | Critical | Missing auth middleware, IDOR, role check gaps |
| Security Misconfiguration | High | Debug in production, permissive CORS, missing headers |
| Cross-Site Scripting | High | innerHTML with user data, dangerouslySetInnerHTML |
| Insecure Deserialization | High | pickle.loads, ObjectInputStream, unvalidated JSON.parse |
| Vulnerable Components | Medium | Outdated packages, no lockfile, no audit in CI |
| Insufficient Logging | Medium | No auth event logging, swallowed errors |
| Secret Management | Critical | API keys in source, .env committed to git |
| CSRF Protection | High | State-changing GET requests, missing CSRF middleware |
| Rate Limiting | Medium | No throttle on auth endpoints |
| Input Validation | High | Regex-only validation, trusting client-side checks |
Patterns in Detail
1. Injection (SQL, NoSQL, Command, LDAP)
Red Flags: String concatenation in SQL; exec/subprocess.call(shell=True) with user values; ORM raw queries unparameterized.
// BEFORE — SQL injection: attacker sends "1 OR 1=1"
const rows = await db.query(`SELECT * FROM orders WHERE user_id = '${req.params.id}'`);
// AFTER — parameterized query
const rows = await db.query('SELECT * FROM orders WHERE user_id = $1', [req.params.id]);
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.
- 9d ago First seen · 316 lines · 80 tokens per session scan A d8825d59c7eb
security-patterns-code-review is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 2,641 once invoked, about $0.0004 per session on Opus 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…