LLM Evaluation System is an agent-guided platform for evaluating language models and agents, generating datasets and configuring multiple judges from natural-language requests before producing an analysis report. It is for comparing model responses, testing agents, and creating document-grounded evaluation data.
Borrowing it
Nothing to install: this file belongs to awslabs/llm-evaluation-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/awslabs/llm-evaluation-system/main/.claude/skills/aws-architecture/SKILL.mdgit clone --depth 1 https://github.com/awslabs/llm-evaluation-systemWrote 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/skills/awslabs/llm-evaluation-system/aws-architecture)<a href="https://agentmods.dev/skills/awslabs/llm-evaluation-system/aws-architecture"><img src="https://agentmods.dev/badge/skills/awslabs/llm-evaluation-system/aws-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/skills/awslabs/llm-evaluation-system/aws-architecture"><img src="https://agentmods.dev/badge/skills/awslabs/llm-evaluation-system/aws-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00109 | $0.01885 |
| Opus 5.5 | $0.00044 | $0.00754 |
| Sonnet 5.5 | $0.00022 | $0.00377 |
| Haiku 4.5 | $0.00011 | $0.00188 |
Grade A, and why
aws-architecture scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `scripts/fetch_icons.sh` needs `curl` + `unzip`. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS Architecture Diagram Skill
Build clean, AWS-poster-style architecture diagrams using the official AWS Architecture Icons, authored as a hand-laid-out SVG (inside an HTML wrapper) and rendered to PNG via headless Chromium. This is the approach that reliably avoids the two things that wreck these diagrams: crossing arrows and lines cutting through text.
Why SVG (not draw.io, not HTML/CSS divs)
- The hard part of an architecture diagram is the connectors (routed arrows
between nodes). SVG
<path>with explicit waypoints + a<marker>arrowhead is the only medium where you control every bend, so lines route through gaps and never cross labels. - draw.io's auto-router makes uncontrollable diagonal crossings; CSS has no line primitive (you'd fake arrows with rotated divs — looks bad).
- One SVG coordinate system means icons and line endpoints align exactly, and paint order (lines first, icons second) tucks arrows neatly behind icons.
Workflow
- Fetch icons (once):
bash scripts/fetch_icons.sh— downloads + caches the official AWS icon package undercache/aws-icons/. Idempotent. - Resolve each service icon:
python3 scripts/find_icon.py cache <name>prints the best-match SVG path (e.g.cloudfront,cognito,elastic kubernetes,rds,bedrock,simple storage,elastic load balancing). Use--list <name>to see candidates. Gotcha: general/resource icons ship in_Light(dark glyph) and_Dark(white glyph) variants — on a white canvas always use_Light(the resolver already prefers it). The "User" actor icon isRes_User_48_Light.svg. - Author the SVG (see Template + Layout rules below). Reference icons with
<image href="file:///abs/path/icon.svg" .../>while iterating. - Render:
python3 scripts/render.py diagram.html out.png(screenshots the<svg id="d">). Add--scale 2for crisp output (default 2). - CRITICAL — self-critique loop: actually Read the rendered PNG, list the worst flaw (a line crossing text, a label collision, clipping, an invisible/white icon, an off-center trunk), fix that ONE thing, re-render. Repeat until clean. This loop is the skill — do not stop after one render. Typically 4-6 passes.
- Finalize self-contained: once good, run
python3 scripts/render.py diagram.html out.png --embedto inline the icon SVGs as base64 data URIs (so the source has nofile://deps), then render the final PNG. Commit the.htmlsource + PNG together.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 127 lines · 109 tokens per session scan A 9e264de4253e
aws-architecture is a skill published in the GitHub repository awslabs/llm-evaluation-system (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 1,885 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
aws-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aws-architectureawslabs/llm-evaluation-system | Skill | 26 | yesterday | Apache-2.0 | A | 109 | Claude Code |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| gke-reliabilitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| gke-workload-securitygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 171 | Claude Code, Codex |
| cloud-architectJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 71 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |