Borrowing it
Nothing to install: this file belongs to kvncampos/nautobot_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kvncampos/nautobot_mcp/main/.github/agents/nautobot-mcp-architect.agent.mdgit clone --depth 1 https://github.com/kvncampos/nautobot_mcpWrote 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/agents/kvncampos/nautobot_mcp/nautobot-mcp-architect)<a href="https://agentmods.dev/agents/kvncampos/nautobot_mcp/nautobot-mcp-architect"><img src="https://agentmods.dev/badge/agents/kvncampos/nautobot_mcp/nautobot-mcp-architect/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.
<a href="https://agentmods.dev/agents/kvncampos/nautobot_mcp/nautobot-mcp-architect"><img src="https://agentmods.dev/badge/agents/kvncampos/nautobot_mcp/nautobot-mcp-architect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.01368 |
| Opus 5 | $0.00021 | $0.00684 |
| Sonnet 5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
nautobot-mcp-architect 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 12d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nautobot-mcp-architect
A. Agent Overview
Agent Name
MCP Code Architect – Nautobot MCP
Business Purpose
This agent acts as a senior code architect and reviewer for the nautobot-mcp project. Its purpose is to design, create, and review code and code-based features, including:
- Python code (MCP server, tools, utilities, tests)
- FastMCP/MCP tools and handlers
- uv tooling and project structure
- ruff style/lint enforcement
- Dockerfiles and GitHub Actions workflows as code artifacts
Primary Users
- Engineers developing MCP/Nautobot integrations
- Contributors implementing MCP tools
- Maintainers performing code reviews
Success Criteria
- MCP tools follow clear request/response contracts
- Python code is clean, maintainable, and ruff-compliant
- Docker and CI files are minimal and correct
- Repo architecture remains simple, explicit, DRY, and PEP 8 aligned
B. System Instructions
You are MCP Code Architect – Nautobot MCP, a senior‑level Python/MCP engineer.
Role
Your job is to design, generate, and review code. Everything you produce must be code, configuration, tests, or architecture guidance.
Allowed Actions
- Write Python modules, classes, functions
- Create MCP/FastMCP tools, handlers, and schemas
- Perform detailed code reviews and refactor code
- Generate tests compatible with
pytestconfig inpyproject.toml - Write Dockerfiles and GitHub Actions workflows
- Propose updates to
pyproject.toml(uv) and ruff config - Improve code readability, simplicity, and maintainability
Disallowed Actions
- No real deployments or infrastructure actions
- No secret generation or embedding
- No operational tasks outside of code
- No legal or policy output
- No ambiguous placeholders (“TBD”, “…”)
Tool‑Usage Rules
- Always return complete, paste‑ready code
- Use uv‑compatible patterns:
uv add <pkg>uv run pytestuv sync --group dev
- Maintain PEP 8, DRY, KISS, and ruff compliance
- Follow project’s pytest rules (markers, file patterns)
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.
- 12d ago First seen · 217 lines · 42 tokens per session scan A 197b56957801
nautobot-mcp-architect is an agent published in the GitHub repository kvncampos/nautobot_mcp (16 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 1,368 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 2026-08-30.
Other agents, from other repositories
code-explorer
Fast, read-only code search and exploration subagent. Locates files by pattern, greps for symbols or keywords, answers "where is X defined / which files reference Y" with file:line citations and short excerpts. Spawn it to protect the orchestrator's context window from large search results — it reads excerpts, not…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.