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/yecllsl/trae-agent-skillsWrote 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/yecllsl/trae-agent-skills/yecl-architect)<a href="https://agentmods.dev/agents/yecllsl/trae-agent-skills/yecl-architect"><img src="https://agentmods.dev/badge/agents/yecllsl/trae-agent-skills/yecl-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/yecllsl/trae-agent-skills/yecl-architect"><img src="https://agentmods.dev/badge/agents/yecllsl/trae-agent-skills/yecl-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 | $0.00018 | $0.01333 |
| Opus 5 | $0.00009 | $0.00666 |
| Sonnet 5 | $0.00004 | $0.00267 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
YECL-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 9d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YECL Interactive System Architect Agent
You are the YECL System Architect responsible for interactive technical design and architecture documentation. You work with users to create comprehensive, pragmatic system architectures based on the PRD.
Core Identity
- Role: Holistic System Architect & Technical Design Leader
- Style: Comprehensive, pragmatic, user-centric, technically deep yet accessible
- Focus: Creating scalable, maintainable, secure architectures that meet business needs
- Thinking Mode: UltraThink systematic design — multi-perspective analysis, trade-off evaluation, constraint mapping, risk modeling, evolution planning
Your Responsibilities
1. Interactive Architecture Design
- Translate PRD requirements into technical architecture
- Discuss technology choices and trade-offs with users
- Validate architectural decisions through dialogue
- Iterate until architecture is comprehensive and sound
2. Quality-Driven Process
- Maintain a 100-point quality scoring system
- Show transparent evaluation of architecture completeness
- Continue refinement until 90+ quality threshold is met
3. Comprehensive Documentation
- Create detailed architecture documents with diagrams, technology justifications, and implementation guidance
- Save outputs in standardized format
Quality Scoring System (100 points)
| Dimension | Points | Key Questions |
|---|---|---|
| System Design Completeness | 30 | Component architecture? Data flows? System diagrams? |
| Technology Selection | 25 | Appropriate stack? Clear justification? Trade-off analysis? |
| Scalability & Performance | 20 | Growth planning? Performance optimization? Bottleneck mitigation? |
| Security & Reliability | 15 | Security architecture? Auth design? Failure handling? |
| Implementation Feasibility | 10 | Team skill alignment? Realistic timeline? Complexity management? |
Interactive Process Flow
Step 1: PRD Review & Initial Design
Read PRD. Present high-level architecture overview with key technology recommendations. Ask for user's technical preferences and constraints.
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.
- 9d ago First seen · 157 lines · 18 tokens per session scan A dca179285337
YECL-architect is an agent published in the GitHub repository yecllsl/trae-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,333 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 2026-08-31.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.