security-scanner

security-scanner is an agent for Claude Code from navraj007in/architecture-cowork-plugin. It costs 34 tokens per session (2,092 once invoked), scanned A, original, Apache-2.0.

An agent that checks scaffolded project code against a planned security checklist. It verifies protections such as authentication, cross-origin request rules, request limits, security headers, and input validation.

In plain words
What is it for?
Use it to review a scaffolded project, confirm that the selected identity provider and token model are wired in, and check required web-security protections.
Why use it?
It helps reveal when the generated project does not actually implement security requirements described in its architecture plan.

Agent for Claude Code

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

Part of the architect plugin — 48 skills, 63 commands, 19 agents, 7 MCP servers shipped together

Good fit Use it to review a scaffolded project, confirm that the selected identity provider and token model are wired in, and check required web-security protections.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/navraj007in/architecture-cowork-plugin/security-scanner
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/navraj007in/architecture-cowork-plugin

Made for: Claude Code.

Or install architect, the plugin that ships this one along with the rest of its 48 skills, 63 commands, 19 agents, 7 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-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/security-scanner/github.svg)](https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/security-scanner)
Your own site
<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/security-scanner"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/security-scanner/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-scanner

Your own site · 80×15
<a href="https://agentmods.dev/agents/navraj007in/architecture-cowork-plugin/security-scanner"><img src="https://agentmods.dev/badge/agents/navraj007in/architecture-cowork-plugin/security-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,092 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 $0.00034 $0.02092
Opus 5 $0.00017 $0.01046
Sonnet 5 $0.00007 $0.00418
Haiku 4.5 $0.00003 $0.00209

Measured 11d ago against content hash 6790634ae867, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

security-scanner 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 11d 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-scanner.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Scanner Agent

You are the Security Scanner Agent for the Architect AI plugin. Your job is to validate that the scaffolded project code actually implements the security measures specified in the blueprint's security architecture (deliverable 4f).

Input

You will receive:

  • The security architecture from the blueprint (auth strategy, API security checklist, data protection, OWASP mitigations)
  • The scaffolded project directory path(s)
  • The tech stack (framework, language)
  • auth.identityProvider from SDL (e.g. clerk, auth0, cognito, firebase, custom-jwt) — used to verify the correct provider SDK is wired in auth middleware
  • auth.serviceTokenModel from SDL (jwt | session | api-key) — used to verify the correct token validation mechanism is in place

Process

1. Read Security Checklist

Parse the blueprint's security checklist table to extract all required protections:

Protection Expected Implementation Priority
Rate limiting express-rate-limit or equivalent Must-have
Input validation Zod, Joi, or equivalent Must-have
CORS cors middleware with explicit origins Must-have
Helmet headers helmet middleware Must-have
Auth middleware JWT verification on protected routes Must-have
SQL injection prevention Parameterized queries (ORM) Must-have
File upload validation Type + size checks Should-have

2. Scan Project Files

For each security measure, check if it's present in the codebase:

Auth Middleware Check

Node.js/Express:

Search for: import.*auth|require.*auth|requireAuth|verifyToken|jwt.verify
Files to check: src/middleware/auth.*, src/middleware/*.ts, src/index.ts

Python/FastAPI:

Search for: require_auth|verify_token|HTTPBearer|Depends.*security
Files to check: app/middleware/auth.*, app/main.py, app/dependencies.py

Verify:

  • Auth middleware file exists
  • Middleware is imported in the main app or router
  • Protected routes use the middleware
  • Token validation mechanism matches auth.serviceTokenModel:
    • jwt: look for JWT decode/verify call (e.g. jsonwebtoken.verify, jose.jwtVerify, python-jose)
    • session: look for session cookie parsing (e.g. express-session, Starlette SessionMiddleware)
    • api-key: look for API key header extraction (e.g. req.headers['x-api-key'])
  • If auth.identityProvider is clerk, auth0, cognito, or firebase: verify the correct provider SDK is used (not a generic custom JWT implementation)

Read the full file on GitHub · 244 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. 11d ago First seen · 244 lines · 34 tokens per session scan A 6790634ae867

Subscribe to this mod's changes

security-scanner is an agent published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 2,092 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

section-writer

Generates self-contained implementation section content. Outputs raw markdown. Used by /deep-plan for parallel section generation.

piercelamb/deep-plan · 26 tokens

opus-plan-reviewer

Reviews implementation plans (fallback when external LLMs unavailable).

piercelamb/deep-plan · 17 tokens

spec-scanner

Scans a codebase using LLM-driven heuristics to detect framework, patterns, entities, and registration points. Produces a persistent project profile that other agents read for wiring-aware implementation.

Habib0x0/spec-driven-plugin · 41 tokens

spec-documenter

Generates user-facing documentation from spec files and implemented code. Produces API references, user guides, and architecture decision records. Context: Feature implementation is complete and user needs documentation. user: "/spec-docs" assistant: "I'll generate documentation from the spec and implementation." The…

Habib0x0/spec-driven-plugin · 100 tokens

spec-validator

Use this agent when you need to validate a spec for completeness, consistency, and implementation readiness. Examples: Context: User has finished creating a spec and wants to verify it's ready for implementation. user: "I've finished the spec for user-authentication. Can you validate it?" assistant: "I'll use the…

Habib0x0/spec-driven-plugin · 275 tokens

spec-reviewer

Reviews code quality, security, and architectural alignment after Tester verifies functionality. Uses the reasoning tier for deep reasoning about subtle issues.

Habib0x0/spec-driven-plugin · 29 tokens