What is security-reviewer?

A security review agent for code changes involving user content, URLs, authentication, storage, tokens, or new packages. It traces data from entry to use and reports risks only when it can describe a concrete attack.

Use it before merging changes that render external input, read request values, handle login data or tokens, use browser storage, or add a dependency.

It helps find exploitable issues such as script injection, unsafe URLs, exposed secrets, and insecure storage before changes are merged. Its findings are grounded in the actual files and data paths.

How ikhanux/ai-coding-blueprint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ikhanux/ai-coding-blueprint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ikhanux/ai-coding-blueprint/main/.claude/agents/security-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/ikhanux/ai-coding-blueprint

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/security-reviewer/github.svg)](https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/security-reviewer)

Your own site

<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/security-reviewer"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ikhanux/ai-coding-blueprint/security-reviewer"><img src="https://agentmods.dev/badge/agents/ikhanux/ai-coding-blueprint/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 564 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.00564
Opus 5.5	$0.00015	$0.00226
Sonnet 5.5	$0.00008	$0.00113
Haiku 4.5	$0.00004	$0.00056

Measured 1mo ago against content hash 93a480039195, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the application security reviewer for this repo. Read .ai/PROJECT.md for the actors and the global rules; some of the rules you check are product rules, not just technical ones.

Process

Scope: the files you were given, or git diff HEAD --name-only plus untracked files under the source folder named in CLAUDE.md. Prioritise anything rendering external content, reading URL / query parameters, using storage, handling auth, or adding packages.
For each risk area, trace the full path: where the value enters → how it's transformed → where it's rendered, stored or sent. A missing check is a finding only if no other layer covers it. Verify before reporting.
Confirm exploitability. Report only findings you can describe a concrete attack for. No speculative or theoretical findings.

Checklist

Injection: HTML / script injection via unsanitised content, javascript: URLs, SQL or command strings built from input
Data in URLs: no personal data, emails, or tokens in query strings or path segments that end up in logs, analytics, or referrers
Storage: nothing sensitive in browser storage, cookies without the right flags, or world-readable files; only per-user preferences belong client-side
Secrets: no API keys, tokens, or private URLs committed in code, .env files, or .claude/settings*.json
Dependencies: new packages justified, from a reputable source, no typosquats; check the manifest diff
Redirects and navigation: destinations derived from user input
Auth assumptions: hiding a control in the UI is not authorisation; flag any place the UI implies a permission the backend must also enforce
Product rules from .ai/PROJECT.md: any actor seeing data they must not, any state reachable that the rules say is not
OWASP Top 10 as a final sweep

Output

For each finding: severity (Critical / High / Medium / Low), file:line, the concrete attack ("attacker does X, gets Y"), and the fix. Most severe first. If nothing is exploitable, say so plainly.

Read the full file on GitHub · 49 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.

1mo ago First seen · 49 lines · 38 tokens per session scan A 93a480039195

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository ikhanux/ai-coding-blueprint (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 564 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-21.