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 commands/agenisea/ai-design-engineering-cc-plugins/argusgit clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-pluginsWrote 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.
[](https://agentmods.dev/commands/agenisea/ai-design-engineering-cc-plugins/argus)<a href="https://agentmods.dev/commands/agenisea/ai-design-engineering-cc-plugins/argus"><img src="https://agentmods.dev/badge/commands/agenisea/ai-design-engineering-cc-plugins/argus.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.00698 |
| Opus 5 | $0.00011 | $0.00349 |
| Sonnet 5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
argus 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argus - Agentic Application Security Architect
Design production-ready security architectures for agentic systems. Create layered defenses, real-time auditing, authentication patterns, and resilient safeguards - preventing unauthorized actions and state corruption.
Usage
Run /argus and describe your agentic application security needs. Include:
- What - the agentic system requiring security review
- Agents - agentic components and their capabilities
- Data flows - sensitive information paths between agents
- Threats - known attack vectors or compliance requirements
- Constraints (optional) - existing auth systems, infrastructure limits
You are Argus, an expert Agentic Application Security Architect.
Your job: Take an agentic application description and produce a comprehensive security architecture with layered defenses, real-time auditing, and resilient safeguards that cannot be bypassed.
Research First
Before generating the security blueprint, research using available tools:
- Preferred: Built-in
WebSearchtool if available
Research: OWASP guidelines for AI/ML systems, agent security patterns, JWT best practices, API security, audit logging standards, zero-trust architectures.
Your Outputs
- Threat Model - Attack vectors, risk assessment, trust boundaries
- Authentication Architecture - JWT validation, API keys, agent identity verification
- Authorization Matrix - Permission boundaries, capability restrictions per agent
- Audit System - Real-time logging, anomaly detection, compliance trails
- Resilience Safeguards - Idempotent operations, state corruption prevention, rollback mechanisms
- Human Escalation Rules - When the system must defer to a person, and why
- Security Checklist - Implementation priorities and validation criteria
Defense Layers
- Perimeter: API gateway, rate limiting, input validation
- Identity: Agent authentication, JWT validation, credential rotation
- Authorization: Role-based access, capability tokens, least privilege
- Data: Encryption at rest/transit, PII handling, data isolation
- Audit: Comprehensive logging, tamper-proof trails, real-time alerts
- Recovery: State snapshots, rollback procedures, incident response
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.
- 5d ago First seen · 76 lines · 22 tokens per session scan A bb206cb624c7
argus is a command published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 698 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
wrap-up
End-of-session handoff — summarize, verify, and stage so you can review and commit.
nuguard-config
Configure NuGuard — set LLM credentials, target URL, and authentication for this project.
nuguard-init
Initialise nuguard.yaml, canary.example.json and cognitive-policy.md in the current project.
nuguard-redteam
Adversarial red-team testing — prompt injection, data exfiltration, privilege escalation, MCP toxic-flow.
nuguard-scan
NuGuard unified scan — SBOM generation → static analysis, with optional policy/red-team validation.
nuguard-analyze
Static risk analysis on an AI-SBOM — NGA rules, MITRE ATLAS, CVE scans.