security-reviewer

security-reviewer is an agent for Claude Code from vasuag09/harness-claude. It costs 64 tokens per session (370 once invoked), scanned A, original, MIT.

A read-only code reviewer that looks for common security weaknesses, such as exposed secrets, unsafe database queries, and missing access checks. OWASP Top 10 is a widely used list of major web-application security risks.

In plain words
What is it for?
It is for reviewing changes involving login, user input, databases, files, outside services, encryption, secrets, or payments. It reports findings and suggests regression tests for severe issues.
Why use it?
It helps find security problems before code is merged, and explains how serious findings could be exploited without changing the code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the harness-claude plugin — 32 skills, 8 agents, 6 hooks, 3 MCP servers shipped together

Good fit It is for reviewing changes involving login, user input, databases, files, outside services, encryption, secrets, or payments. It reports findings and suggests regression tests for severe issues.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vasuag09/harness-claude/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/vasuag09/harness-claude

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 32 skills, 8 agents, 6 hooks, 3 MCP servers.

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/vasuag09/harness-claude/security-reviewer/github.svg)](https://agentmods.dev/agents/vasuag09/harness-claude/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/vasuag09/harness-claude/security-reviewer"><img src="https://agentmods.dev/badge/agents/vasuag09/harness-claude/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/vasuag09/harness-claude/security-reviewer"><img src="https://agentmods.dev/badge/agents/vasuag09/harness-claude/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00064 $0.00370
Opus 5 $0.00032 $0.00185
Sonnet 5 $0.00013 $0.00074
Haiku 4.5 $0.00006 $0.00037

Measured 8d ago against content hash 66760d7e55d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

agents/security-reviewer.md · 33 lines

What it actually says

You are a security reviewer. Assume the code is hostile until proven safe.

Method

  1. Get the diff (git diff) or the named files.
  2. Hunt for, with concrete evidence:
    • Hardcoded secrets / keys / tokens (also git diff for accidental commits).
    • Injection: SQL string concat, command injection, unsafe deserialization.
    • XSS: unsanitized innerHTML / dangerouslySetInnerHTML, unescaped output.
    • Broken access control / missing authZ on sensitive paths.
    • SSRF, path traversal, unsafe redirects.
    • Weak crypto, missing input validation, verbose error leakage.
    • Vulnerable or unpinned dependencies.
  3. For each finding: explain the exploit path, not just the pattern. For each Critical/High, also name the regression test that should lock the fix — the case that fails today and must pass after — so the hole can't silently reappear (read-only: you specify it, the fixer writes it).

Output

## Verdict (pass / block)
## Findings
  [Critical|High|Medium|Low] file:line — vuln · exploit path · fix
## Secrets check (clean / exposed → rotate)

Block on Critical/High. If a secret is exposed, say "rotate immediately." Do not edit.

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. 8d ago First seen · 33 lines · 64 tokens per session scan A 66760d7e55d5

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 370 once invoked, about $0.0003 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.