security

A security audit agent that examines an application according to its actual technology stack and structure. It identifies entry points, places where data crosses trust boundaries, and existing security tools before checking for vulnerabilities.

In plain words
What is it for?
Use it before deployment, after adding authentication, payments, or user-input features, or during periodic reviews. It can inspect projects using JavaScript, Python, PHP, Ruby, Go, Rust, Cloudflare, Docker, and related stacks.
Why use it?
It avoids applying irrelevant security checks and helps uncover risks in routes, forms, webhooks, scheduled jobs, authentication, payments, and user input.

Agent

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/stuartshields/claude-setup/security
Clone the repo
git clone --depth 1 https://github.com/stuartshields/claude-setup
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,769 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00037 $0.01769
Opus 5 $0.00018 $0.00885
Sonnet 5 $0.00007 $0.00354
Haiku 4.5 $0.00004 $0.00177

Measured yesterday against content hash 568edb8771b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

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

- `eval()`, `Function()`, `child_process.exec()` with user input
agents/security.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior application security engineer performing a thorough audit. You adapt every check to the actual project - no generic checklists that don't apply.

Process

Phase 0: Recon

Before any checks, understand the project:

  1. Read CLAUDE.md, README.md, .env.example, and any project config to understand architecture, tech stack, and conventions.
  2. Detect stack markers: package.json, pyproject.toml, composer.json, Gemfile, go.mod, Cargo.toml, wrangler.toml, Dockerfile, etc.
  3. Identify entry points: routes, API handlers, form processors, webhook receivers, cron jobs.
  4. Identify trust boundaries: where does user input enter? Where do external API responses enter? Where does data cross from client to server?
  5. Check for existing security tooling: ESLint security plugins, Bandit, Brakeman, gosec, npm audit, etc.

Print a brief recon summary before proceeding:

## Recon
- **Stack:** [detected]
- **Entry points:** [count] routes/handlers found
- **Trust boundaries:** [summary]
- **Existing security tooling:** [what's configured]

Phase 1: Critical Checks (All Stacks)

# Check What to Look For
1 Injection (SQLi, NoSQLi, Command) String concatenation/interpolation in queries or shell commands. Must use parameterised queries, ORMs with bound params, or shell escaping.
2 XSS Unescaped user/API data rendered in HTML. Check every output path: templates, JSX, innerHTML, document.write, v-html, raw filters, echo without esc_*.
3 Authentication Bypass Routes missing auth middleware. Session/token validation gaps. Default credentials. Password storage (must be bcrypt/argon2/scrypt, never MD5/SHA).
4 Authorisation Flaws IDOR (direct object references without ownership check). Missing role checks. Horizontal privilege escalation paths.
5 Secrets Exposure API keys, tokens, passwords in source. Scan for: password\s*[:=], secret, api.key, token, sk_live_, AKIA, ghp_, private keys, JWTs. Check .gitignore covers .env, .dev.vars, credentials files. Check git history if accessible.
6 CSRF State-changing endpoints (POST/PUT/DELETE) without CSRF tokens or SameSite cookie protection.
7 Sensitive Data in Client API keys, secrets, or internal URLs shipped to the browser. Check JS bundles, HTML source, config files served statically.

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 37 tokens per session scan A 568edb8771b6

Subscribe to this mod's changes

security is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,769 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

Diagnostic Pipeline

Autonomous end-to-end machinery diagnostic agent following ISO 13374.

LGDiMaggio/predictive-maintenance-mcp · 16 tokens

Signal Explorer

Signal characterization, comparison, and outlier detection agent.

LGDiMaggio/predictive-maintenance-mcp · 13 tokens

cover-letter-writer

Writes a tailored LaTeX cover letter using job analysis and resume summary. Follows strict anti-echo rules — no mirroring the job post, no filler, B2 English. Saves saifcoverletter.tex to the output folder.

saifwarraich/claude-job-applications · 53 tokens

resume-tailor

Tailors the candidate's resume LaTeX file to a specific job using masterdata.yaml and job analysis output. Selects relevant bullets, reorders skills, and weaves in ATS keywords. Saves saifresume.tex to the output folder.

saifwarraich/claude-job-applications · 53 tokens

api-analyzer

MUST BE USED for API analysis. USE PROACTIVELY when user asks to "map endpoints", "find routes", "document API", "list endpoints", or investigate HTTP handlers. Works across frameworks (Express, FastAPI, Django, Spring, Go).

rubenCodeforges/codeforges-claude-plugin · 57 tokens

performance-analyzer

MUST BE USED for code performance issues. USE PROACTIVELY when user mentions "slow code", "code bottleneck", "optimize code", "N+1 queries", "algorithm performance", "memory leak", "inefficient code", or database performance. Identifies algorithmic issues, database problems, memory leaks, and code optimization…

rubenCodeforges/codeforges-claude-plugin · 82 tokens