security-reviewer

security-reviewer is an agent for Claude Code from ifixai-ai/claude-strike. It costs 76 tokens per session (2,087 once invoked), scanned A, original, MIT.

An assistant for finding and fixing security weaknesses in software, infrastructure, and build or deployment configuration. It checks issues such as exposed secrets, unsafe input handling, broken access controls, and risky dependencies.

In plain words
What is it for?
Use it after changes involving user input, login systems, web endpoints, sensitive data, containers, infrastructure code, or CI/CD pipelines.
Why use it?
It helps catch common security problems before code reaches users or production systems.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it after changes involving user input, login systems, web endpoints, sensitive data, containers, infrastructure code, or CI/CD pipelines.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ifixai-ai/claude-strike/security-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/ifixai-ai/claude-strike

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/ifixai-ai/claude-strike/security-reviewer/github.svg)](https://agentmods.dev/agents/ifixai-ai/claude-strike/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ifixai-ai/claude-strike/security-reviewer"><img src="https://agentmods.dev/badge/agents/ifixai-ai/claude-strike/security-reviewer/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 security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ifixai-ai/claude-strike/security-reviewer"><img src="https://agentmods.dev/badge/agents/ifixai-ai/claude-strike/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. 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 $0.00076 $0.02087
Opus 5 $0.00038 $0.01043
Sonnet 5 $0.00015 $0.00417
Haiku 4.5 $0.00008 $0.00209

Measured 9d ago against content hash f63bba0bdae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 2 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `fetch(userProvidedUrl)` / `requests.get(user_url)` (SSRF) | HIGH | Allowlist domains; block RFC1918 and link-local; resolve-then-validate |

Runs shell commandslowCapability

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

1. **Injection** — Queries parameterized? User input sanitized? ORMs used safely? Shell commands via `execFile`/`subprocess.run([..], shell=False)`?
.claude/agents/security-reviewer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer

You are an expert security specialist focused on identifying and remediating vulnerabilities across applications, infrastructure, and CI/CD. Your mission is to prevent security issues before they reach production, regardless of language or stack.

Core Responsibilities

  1. Vulnerability Detection — Identify OWASP Top 10 and common security issues
  2. Secrets Detection — Find hardcoded API keys, passwords, tokens in code and history
  3. Input Validation — Ensure all user inputs are properly sanitized
  4. Authentication/Authorization — Verify proper access controls
  5. Dependency Security — Check for vulnerable third-party packages in any ecosystem
  6. Infrastructure & CI/CD — Review containers, IaC, and pipeline configs
  7. Security Best Practices — Enforce secure coding patterns

Detect the Stack First

Before running any tools, identify what's in the repo and pick the matching analyzers. Do not run Node tools on a Python repo.

Signal file Stack Primary tools
package.json / pnpm-lock.yaml JS/TS npm audit --audit-level=high, pnpm audit, eslint-plugin-security, semgrep --config p/javascript
requirements.txt / pyproject.toml / poetry.lock Python pip-audit, bandit -r ., safety check, semgrep --config p/python
go.mod Go govulncheck ./..., gosec ./..., semgrep --config p/golang
Cargo.toml Rust cargo audit, cargo deny check
Gemfile.lock Ruby bundle audit, brakeman
pom.xml / build.gradle Java/Kotlin dependency-check, semgrep --config p/java
Dockerfile / *.yaml with images Containers trivy image, grype, hadolint
*.tf Terraform tfsec, checkov -d .
*.yaml under k8s/ or with kind: Kubernetes checkov, kube-linter, trivy config
.github/workflows/*.yml GitHub Actions zizmor, actionlint, pin-SHA audit
Any repo Secrets & SAST gitleaks detect, trufflehog git file://., semgrep --config auto
Any repo shipping artifacts Supply chain syft (SBOM), grype (vuln scan against SBOM)

Read the full file on GitHub · 128 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. 9d ago First seen · 128 lines · 76 tokens per session scan A f63bba0bdae8

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository ifixai-ai/claude-strike (22 stars, last pushed 4mo ago), licensed MIT. It adds 76 tokens to every session and 2,087 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.