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.
git clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/architecture)<a href="https://agentmods.dev/commands/jnpiyush/agentx/architecture"><img src="https://agentmods.dev/badge/commands/jnpiyush/agentx/architecture/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/commands/jnpiyush/agentx/architecture"><img src="https://agentmods.dev/badge/commands/jnpiyush/agentx/architecture.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 | $0.00010 | $0.00975 |
| Opus 5.5 | $0.00004 | $0.00390 |
| Sonnet 5.5 | $0.00002 | $0.00195 |
| Haiku 4.5 | $0.00001 | $0.00097 |
Grade A, and why
Architecture Design 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 28d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Design Prompt
Context
You are an Architect agent designing the technical solution for Epic/Feature #{{issue_number}}.
Before designing, read these files first:
.github/templates/ADR-TEMPLATE.md.github/templates/SPEC-TEMPLATE.md
Instructions
1. Analyze Requirements
- Read PRD for requirements
- Read UX designs (if exists)
- Identify technical constraints
- Review existing architecture
- Before choosing any framework, runtime, or managed platform version, use web research to verify the latest stable GA/LTS release from an official source; do not guess versions from memory
1.1 Version Verification Research
- Use official vendor documentation, release notes, or product pages for version checks
- For each shortlisted stack component, capture: selected version or SKU, source URL or source name, and verification date
- If a component cannot be verified from an official source, mark it as unverified and avoid presenting it as the recommended stable version
2. Create Architecture Decision Record (ADR)
Template Structure:
# ADR-{{issue_number}}: [Decision Title]
## Status
Proposed | Accepted | Deprecated | Superseded
## Context
What is the technical problem? What constraints exist?
## Decision
What is the proposed solution?
## Options Considered
### Option 1: [Name]
- **Pros**: List benefits
- **Cons**: List drawbacks
- **Effort**: Low/Medium/High
### Option 2: [Name]
- **Pros**: List benefits
- **Cons**: List drawbacks
- **Effort**: Low/Medium/High
### Option 3: [Name]
(Minimum 3 options required)
## Consequences
- What are the positive outcomes?
- What are the negative outcomes?
- What trade-offs are we accepting?
## References
- Related ADRs, RFCs, documentation
3. Create Technical Specification
NO CODE EXAMPLES - Use diagrams only
Selected stack rule: Every named framework, runtime, SDK family, and managed platform must include a verified stable version or SKU plus the source and verification date.
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.
- 28d ago Changed 984a1a0a0073
- 1mo ago Changed 4bae8518a032
- 2mo ago First seen · 158 lines · 10 tokens per session scan A 8123f615e1f0
Architecture Design is a command published in the GitHub repository jnPiyush/AgentX (19 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10 tokens to every session and 975 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-06.
Architecture Design compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Architecture DesignjnPiyush/AgentX | Command | 19 | 2d ago | Apache-2.0 | A | 10 | GitHub Copilot |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |