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.
npx agentmods add agents/nxtg-ai/forge-plugin/securitygit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.02068 |
| Opus 5 | $0.00000 | $0.01034 |
| Sonnet 5 | $0.00000 | $0.00414 |
| Haiku 4.5 | $0.00000 | $0.00207 |
Grade A, and why
security 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security
Dedicated vulnerability hunter -- scans dependencies, detects secrets in source, audits authentication flows, and checks your code against the OWASP Top 10.
| Level | L1 Vibe Coder |
| Category | Domain Specialist |
| Model | Sonnet |
What It Does
The Security agent is a focused penetration tester for your codebase. While the Guardian runs security as one dimension of its broad quality gate, the Security agent goes deep -- it checks all ten OWASP categories, audits authentication and authorization implementations, validates CSP and CORS configurations, scans for secrets with pattern matching, and classifies every finding by severity with specific remediation steps.
What makes this agent valuable is the depth of its security knowledge. It does not just run npm audit. It reads your authentication code and checks for common JWT mistakes (missing expiration, weak signing algorithms, tokens in localStorage). It scans your API endpoints for missing rate limiting, input validation without schema enforcement, and CORS configurations that allow any origin. It checks your frontend for dangerouslySetInnerHTML with user-controlled input, eval() calls, and missing Content Security Policy headers.
Every finding follows a structured format: severity, file location, issue description, attacker impact, and specific code fix. A finding like "HIGH: Hardcoded API key in src/services/github.ts:42" is immediately actionable. The Security agent does not leave you with vague warnings -- it tells you what is wrong, why it matters, and exactly how to fix it.
When to Use It
- Before a release: When you need a comprehensive security audit that goes beyond dependency scanning into code-level vulnerability assessment.
- After implementing authentication: When you have built JWT, OAuth, session management, or any auth system and want an expert review for common security mistakes.
- When onboarding third-party dependencies: When you have added new packages and want to verify they do not introduce known vulnerabilities or problematic licenses.
- After a security incident: When you need to find all instances of a vulnerability pattern across the codebase, not just the one that was exploited.
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.
- yesterday First seen · 141 lines · 0 tokens per session scan A 4acef2bea166
security is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,068 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.