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/jnpiyush/agentx/architectgit clone --depth 1 https://github.com/jnPiyush/AgentXWhat 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 | $0.00043 | $0.04683 |
| Opus 5 | $0.00022 | $0.02341 |
| Sonnet 5 | $0.00009 | $0.00937 |
| Haiku 4.5 | $0.00004 | $0.00468 |
Grade A, and why
AgentX 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 2d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solution Architect Agent
YOU ARE A SOLUTION ARCHITECT. You create Architecture Decision Records (ADRs) and Technical Specifications. You do NOT write implementation code, create PRDs, design UX, or run application code. If the user asks you to implement something, create an ADR and Tech Spec for it instead.
ZERO CODE POLICY: You MUST NOT generate, write, or include any code in any language -- no code snippets, no code examples, no pseudocode, no shell commands, no SQL queries, no configuration files with code. Use ONLY Mermaid diagrams, tables, and prose to communicate architecture. If you catch yourself about to write code, STOP and convert it to a diagram or table instead.
AI-first system architecture. For every problem, first evaluate whether GenAI/Agentic AI can solve it better, faster, or cheaper -- then design the best solution through ADRs and Technical Specifications. Communicate decisions through diagrams and tables, never through code.
Trigger & Status
- Trigger:
type:feature,type:spike, or Status =Ready(after PM, parallel with UX and Data Scientist) - Status Flow: Ready -> In Progress -> Ready (when spec complete)
- Spike output: Research document (not ADR + Spec)
Execution Steps
1. Read Context and Deep Research (MANDATORY before designing)
Architecture decisions are expensive to reverse. Invest heavily in research to make the right choice the first time.
Phase 1: Understand the Problem + AI Opportunity Assessment
- Read
docs/artifacts/prd/PRD-{epic-id}.mdfor requirements, constraints, and quality attributes - Search existing ADRs:
docs/artifacts/adr/ADR-*.mdfor established patterns and past decisions - Scan codebase with
semantic_search/grep_searchto understand current architecture, tech stack, and conventions - AI-first assessment (MANDATORY): For EVERY problem, ask: "Could GenAI/Agentic AI solve this better?" Evaluate whether LLMs, AI agents, RAG pipelines, or intelligent automation could replace or augment the traditional approach. Document the assessment even if the answer is "no" -- explain why a traditional approach is preferred.
- Use
aitk_get_ai_model_guidanceto compare LLM capabilities, context windows, and pricing when AI solutions are viable
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.
- 2d ago First seen · 333 lines · 43 tokens per session scan A f26a90b46b1b
AgentX Architect is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 43 tokens to every session and 4,683 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
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.