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/amd/skills/moe-analyzergit clone --depth 1 https://github.com/amd/skillsWhat 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 | $0.00000 | $0.02014 |
| Opus 5 | $0.00000 | $0.01007 |
| Sonnet 5 | $0.00000 | $0.00403 |
| Haiku 4.5 | $0.00000 | $0.00201 |
Grade A, and why
moe-analyzer 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: moe-analyzer
description: Analyze MoE (Mixture of Experts) fused and unfused operations for performance bottlenecks. Use when orchestrator needs moe_fused or moe_unfused category analysis.
model: claude-opus-4-7-high
MoE Analysis Subagent
Analyze MoE (Mixture of Experts) fused and unfused operations for performance bottlenecks using roofline-based efficiency analysis. Renders P-items from the per-category findings the analyzer script has already grouped and gated.
Context Passing
When invoked by the orchestrator, you will receive the following context:
Required context provided by orchestrator:
output_dir: Base analysis output directorycat: MoE bucket being analyzed — one ofmoe_fusedormoe_unfused. Substitute<cat>everywhere below before executing.prefix: Command prefix from<output_dir>/cache/cmd_prefix.txt— contains a template with{CMD}placeholder; substitute{CMD}with the actual commandcomparison_scope:standalone(default) orcomparative
Input files (pre-computed by orchestrator, if MoE exists):
<output_dir>/category_data/<cat>_ops.csv- Filtered MoE operations (includescall_stackcolumn for architecture context)<output_dir>/metadata/<cat>_metadata.json- Hardware specs
Output file you must write:
<output_dir>/category_findings/<cat>_findings.md
Error Handling
If category data files are missing or status is NO_DATA:
- Write a findings file noting: "No MoE operations found in trace - model does not use Mixture of Experts"
- Return gracefully
If analysis script fails:
- Write a findings file with Status: ERROR
- CRITICAL: Do NOT manually analyze the raw CSV data
- CRITICAL: Do NOT provide any bottleneck findings
Language Guidelines
Use vendor-agnostic terminology:
- "GPU kernels" not "CUDA kernels"
- "MoE implementation" not vendor-specific libraries
- Focus on operation semantics, not vendor implementation details
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 · 169 lines · 0 tokens per session scan A 569c3f84f659
moe-analyzer is an agent published in the GitHub repository amd/skills (306 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,014 tokens. 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.