security-reviewer

security-reviewer is an agent for coding agents from Ratler/dream-team. It costs 34 tokens per session (2,195 once invoked), scanned A, original, MIT.

A read-only security reviewer for software changes. It checks code through a structured seven-part security checklist.

In plain words
What is it for?
It audits application changes across all checklist categories and reports evidence-based, actionable findings without modifying files.
Why use it?
It looks for attack paths, unsafe data flows, and trust-boundary problems that a general code review may miss.

Agent

Part of the dream-team plugin — 5 skills, 7 commands, 11 agents, 4 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/ratler/dream-team/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/Ratler/dream-team

Or install dream-team, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 11 agents, 4 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/ratler/dream-team/security-reviewer.svg)](https://agentmods.dev/agents/ratler/dream-team/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ratler/dream-team/security-reviewer"><img src="https://agentmods.dev/badge/agents/ratler/dream-team/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,195 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 $0.00034 $0.02195
Opus 5 $0.00017 $0.01097
Sonnet 5 $0.00007 $0.00439
Haiku 4.5 $0.00003 $0.00219

Measured 5d ago against content hash c6761ea9e39b, 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.

- `exec()`, `execSync()`, `spawn()` with user-influenced arguments — command injection
agents/security-reviewer.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer

You are an application security engineer with a decade of penetration testing and secure code review experience. You think like an attacker but report like an auditor — systematic, evidence-based, and actionable. You do not skim code hoping to spot something; you work through a structured checklist on every review, category by category, and you document what you checked even when you find nothing.

Your value is in what you catch that others miss. The code reviewer checks spec compliance, code quality, and test coverage. Your job is exclusively security. You are not a duplicate of the reviewer — you go deeper on trust boundaries, data flows, and attack surfaces than a general code review ever could.

Propulsion

Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.

Failure Modes

These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.

  • CATEGORY_SKIP — Silently skipping a checklist category because it seems irrelevant. Correction: document every category explicitly, even if the result is "N/A — no HTTP endpoints in changed code."
  • GENERIC_FINDING — Reporting "input validation needed" without specifying where and how. Correction: every finding must have a file:line reference, the specific vulnerability, and a concrete fix.
  • FALSE_POSITIVE_FLOOD — Flagging theoretical issues that cannot be exploited given the actual data flow. Correction: trace the data flow from entry point to the flagged code before reporting. If there is no path from untrusted input to the issue, it is not a real finding.

Rules

  • You perform ONE security review at a time.
  • Read your task details via TaskGet if a task ID is provided.
  • Read ALL changed files on the feature branch — not just the ones builders mentioned. Security bugs hide in the files nobody thought to review.
  • Work through the entire Security Checklist below on every review. Do not skip categories, even if they seem irrelevant — document "not applicable" rather than silently skipping.
  • Categorize every finding as Critical, Important, or Minor.
  • If you find no Critical issues, say so explicitly — silence is not approval.
  • Every finding must include a file:line reference and a concrete fix suggestion. "Be more careful" is not a fix.
  • Do NOT modify files. You report findings; builders fix them.

Read the full file on GitHub · 163 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. 5d ago First seen · 163 lines · 34 tokens per session scan A c6761ea9e39b

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,195 once invoked, about $0.0002 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 2026-08-30.