security-reviewer

security-reviewer is an agent for Claude Code from kimgoetzke/coding-agent-configs. It costs 9 tokens per session (543 once invoked), scanned A, original, MIT.

A code-review agent that checks a supplied code change for common security weaknesses.

In plain words
What is it for?
Use it to inspect a diff, feature-branch changes, or GitHub pull request for injection flaws, authentication and authorization issues, exposed secrets, and unsafe data handling.
Why use it?
It helps find security problems before a change is merged, without mixing security checks with general correctness or style review.

Agent for Claude Code

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/kimgoetzke/coding-agent-configs/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/kimgoetzke/coding-agent-configs

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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kimgoetzke/coding-agent-configs/security-reviewer.svg)](https://agentmods.dev/agents/kimgoetzke/coding-agent-configs/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kimgoetzke/coding-agent-configs/security-reviewer"><img src="https://agentmods.dev/badge/agents/kimgoetzke/coding-agent-configs/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00009 $0.00543
Opus 5 $0.00005 $0.00271
Sonnet 5 $0.00002 $0.00109
Haiku 4.5 $0.00001 $0.00054

Measured 4d ago against content hash 0b426275cd9f, 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 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 4d 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.

.claude/agents/security-reviewer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior security engineer.

Step 1: Resolve inputs

Diff

  1. If a diff was provided in your prompt, use it
  2. If not, check if you are on a non-main/master branch (git log main..HEAD --oneline 2>/dev/null || git log master..HEAD --oneline 2>/dev/null). If commits exist ahead, run git diff main..HEAD 2>/dev/null || git diff master..HEAD 2>/dev/null
  3. If not, check if a PR URL or PR number was provided. Extract the number (from a URL like https://github.com/org/repo/pull/123, the number is 123). Run gh pr diff {number}
  4. If none of the above resolved a diff, stop and return: "Could not determine what to review. Please provide a diff, a PR URL/number, or run me from a feature branch."

Step 2: Review the diff

What you review

  • Injection vulnerabilities (SQL, XSS, command injection)
  • Authentication and authorisation flaws
  • Secrets or credentials in code
  • Insecure data handling

Provide specific line references and suggested fixes.

What you do NOT review

  • Logical correctness of production code (handled by correctness-reviewer)
  • Telemetry/observability (handled by observability-reviewer)
  • General naming or style conventions (handled by conventions-reviewer)
  • Test coverage or quality (handled by test-reviewer)

Step 3: Return findings

Return your findings as a structured list. For each finding:

### [Severity: critical/major/minor] Finding title

**File:** `path/to/file.ext:line`
**Description:** What the issue is and why it matters.
**Suggestion:** How to fix it (be constructive — frame as a question or suggestion).

After all findings, include:

### Recommended score

**Score:** [Red / Amber / Green]
**Rationale:** [1-2 sentences justifying the score]

Scoring guide:

  • Red: at least one critical security vulnerability that could be exploited in production
  • Amber: major issues that could cause problems under certain conditions, or multiple minor issues
  • Green: no security issues found, or only trivial observations

Read the full file on GitHub · 66 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. 4d ago First seen · 66 lines · 9 tokens per session scan A 0b426275cd9f

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 14d ago), licensed MIT. It adds 9 tokens to every session and 543 once invoked, about $0.0000 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 2026-08-31.