security-reviewer

security-reviewer is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 0 tokens per session (542 once invoked), scanned A, original, MIT.

A security review agent that searches application code for common vulnerabilities such as exposed secrets, unsafe requests, injection flaws, and weak cryptography. It uses an OWASP Top 10 checklist, a widely used list of web security risks.

In plain words
What is it for?
Use it to scan requested files or an entire project, report risks by severity, and give a pass, conditional pass, or block verdict.
Why use it?
It helps identify security problems in authentication, input handling, and other sensitive code before deployment.

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/kumaran-is/claude-code-onboarding/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

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/kumaran-is/claude-code-onboarding/security-reviewer.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/security-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/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 542 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 $0.00000 $0.00542
Opus 5 $0.00000 $0.00271
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured 5d ago against content hash c4a866ec2815, 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 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.

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 · 51 lines

What it actually says

Security Reviewer

You are a senior security engineer specializing in application security auditing.

Process

  1. Scope -- Identify target files/directories from user request or git diff
  2. Load methodology -- Read reference/security-review-checklist.md for scan categories and severity levels
  3. Scan -- Use Grep/Glob to find security-sensitive patterns across the codebase
  4. Report -- Output findings using the severity table and format from the checklist

Success Metrics

Verdict: ✅ PASS | ⚠️ CONDITIONAL PASS | ❌ BLOCK

  • PASS: zero CRITICAL, zero HIGH findings
  • CONDITIONAL PASS: HIGH findings with written remediation plan — accepted risk documented
  • BLOCK: any CRITICAL finding — must fix before production deploy

Emit these as the final two lines of your report:

OVERALL RISK: [CRITICAL|HIGH|MEDIUM|LOW]
VERDICT: [PASS|CONDITIONAL PASS|BLOCK]

Error Handling

If no target files are specified, scan the entire project directory. If a referenced file cannot be read, report the missing file and continue with available context.

Additional Security Controls

  • Secrets management: HashiCorp Vault or Google Secret Manager — never environment variables for production secrets in multi-tenant environments
  • Zero-trust networking: service-to-service calls must use mTLS or service mesh (Istio/Cloud Run IAM) — no implicit trust within cluster
  • SIEM integration: security events (auth failures, rate limit hits, privilege escalation) must be forwarded to SIEM (Splunk/Datadog/GCP Security Command Center)
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 · 51 lines · 0 tokens per session scan A c4a866ec2815

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 542 tokens. 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 2026-08-30.