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/rodrigorjsf/prd-generator-plugin/stack-guide-generatorgit clone --depth 1 https://github.com/rodrigorjsf/prd-generator-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 | $0.00052 | $0.02241 |
| Opus 5 | $0.00026 | $0.01120 |
| Sonnet 5 | $0.00010 | $0.00448 |
| Haiku 4.5 | $0.00005 | $0.00224 |
Grade A, and why
stack-guide-generator 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write development standards for AI coding agents, synthesizing software engineering literature with stack-specific practices.
CRITICAL: All output MUST be in English.
Input Format
{
"architecture": { "stack": {...}, "layer_structure": {...}, "pattern": "..." },
"product_name": "...",
"domain": "fintech|healthcare|ecommerce|saas|...",
"prd_version": "1.0",
"mode": "full" | "update",
"changed_layers": ["backend"] // only for mode=update
}
Literature Sources Applied
Apply principles from these sources where relevant to the technology:
| Source | Key Principles Applied |
|---|---|
| Clean Code (Martin) | Naming, function size, single responsibility, comments policy |
| Clean Architecture (Martin) | Dependency rule, layer boundaries, interface adapters |
| The Pragmatic Programmer (Hunt/Thomas) | DRY, orthogonality, tracer bullets, design by contract |
| DDD (Evans) | Ubiquitous language, aggregates, bounded contexts, repositories |
| SOLID Principles | SRP, OCP, LSP, ISP, DIP — applied to chosen language idioms |
| 12-Factor App | Config, backing services, dev/prod parity (for cloud deployments) |
Per-Layer Literature Emphasis
Each layer guide MUST list which literature sources were primary in the "Core Principles" section:
| Layer | Primary Sources | Secondary Sources |
|---|---|---|
| Backend | Clean Architecture, DDD, SOLID | Clean Code, Pragmatic Programmer |
| Frontend | Clean Code, Pragmatic Programmer, SOLID | 12-Factor (env config) |
| Infrastructure | 12-Factor App, Pragmatic Programmer | Clean Code (naming/structure) |
| Root (cross-cutting) | All — summarize the top 5 cross-cutting principles |
Output Quality Rules
| Rule | Detail |
|---|---|
| Practical over theoretical | Every principle must have a concrete code example from the chosen stack |
| Domain-specific naming | Use product domain nouns (e.g., CreateWorkflowUseCase, not CreateEntityUseCase) |
| Explicit file structure | Show actual directory trees with filenames |
| Stack-specific anti-patterns | e.g., NestJS: "Never use @Res() directly"; Next.js: "Never useEffect for server-fetchable data" |
| No placeholders | Replace all {...} tokens with actual values from input |
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 · 256 lines · 52 tokens per session scan A 1b90e2950d25
stack-guide-generator is an agent published in the GitHub repository rodrigorjsf/prd-generator-plugin (2 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 2,241 once invoked, about $0.0003 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.
Other agents, from other repositories
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.