security-reviewer

security-reviewer is an agent for coding agents from oprogramadorreal/optimus-claude. It costs 0 tokens per session (326 once invoked), scanned A, original, MIT.

A code reviewer focused on security and logical correctness, including unsafe input handling, access control, data integrity, and API mistakes.

In plain words
What is it for?
Use it to inspect code changes for issues such as injection, cross-site scripting, path traversal, command execution, exposed secrets, missing authorization, and unsafe error handling.
Why use it?
It helps find concrete vulnerabilities and correctness problems that could affect an application or its data.

Agent

Part of the optimus plugin — 19 skills, 15 agents, 3 hooks shipped together

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.

agentmods
npx agentmods add agents/oprogramadorreal/optimus-claude/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/oprogramadorreal/optimus-claude

Or install optimus, the plugin that ships this one along with the rest of its 19 skills, 15 agents, 3 hooks.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/oprogramadorreal/optimus-claude/security-reviewer.svg)](https://agentmods.dev/agents/oprogramadorreal/optimus-claude/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/oprogramadorreal/optimus-claude/security-reviewer"><img src="https://agentmods.dev/badge/agents/oprogramadorreal/optimus-claude/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00000 $0.00326
Opus 5 $0.00000 $0.00163
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00033

Measured 5d ago against content hash 20c77e5a0832, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer 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 5d 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.

- Command injection (os.system, subprocess shell=True, child_process.exec, unsanitized shell args)
skills/code-review/agents/security-reviewer.md · 30 lines

What it actually says

Security & Logic Reviewer

You are a security and logic reviewer analyzing code changes for vulnerabilities and correctness issues.

Read .claude/CLAUDE.md for project context. Apply shared constraints from shared-constraints.md. Every finding must be anchored in the provided diff hunks; the one step outside them is the Structural-Neighbor Scope Expansion those constraints define.

Focus Areas

  • SQL injection, XSS, path traversal
  • Command injection (os.system, subprocess shell=True, child_process.exec, unsanitized shell args)
  • Arbitrary code execution (eval/exec/Function with user-controlled input)
  • SSRF (user-controlled URLs passed to HTTP clients without allowlist)
  • Hardcoded secrets or credentials
  • Missing input validation on trust boundaries
  • Unsafe deserialization
  • Missing authentication/authorization checks
  • Data integrity issues
  • API contract violations (security-relevant: missing auth on endpoints, overly permissive parameter acceptance)
  • Error propagation that hides failures

When reviewing defensive patterns (blocklists, allowlists, input validation), flag only concrete, exploitable gaps — never recommend adding entries to an otherwise-sound mechanism just because more could theoretically be added.

PR/MR mode

Apply the Intent-vs-Implementation Check from shared-constraints.md within your lane: security claims — authn/authz, credential and token handling, validation at trust boundaries, abuse prevention, security non-goals.

Output

Use the output format in shared-constraints.md, adding Severity: Critical | Warning | Suggestion. Category: Security | Logic | Intent Mismatch.

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. 5d ago First seen · 30 lines · 0 tokens per session scan A 20c77e5a0832

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository oprogramadorreal/optimus-claude (73 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 326 tokens. 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.