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 skills add seandkendall/kiro-config --skill aws-diagram-htmlgit clone --depth 1 https://github.com/seandkendall/kiro-configWrote 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/seandkendall/kiro-config/aws-diagram-html)<a href="https://agentmods.dev/skills/seandkendall/kiro-config/aws-diagram-html"><img src="https://agentmods.dev/badge/skills/seandkendall/kiro-config/aws-diagram-html/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/seandkendall/kiro-config/aws-diagram-html"><img src="https://agentmods.dev/badge/skills/seandkendall/kiro-config/aws-diagram-html.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 | $0.00083 | $0.01982 |
| Opus 5.5 | $0.00033 | $0.00793 |
| Sonnet 5.5 | $0.00017 | $0.00396 |
| Haiku 4.5 | $0.00008 | $0.00198 |
Grade A, and why
aws-diagram-html 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 today.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS Diagram HTML (SVG, official icons, no overlapping lines)
Produces docs/architecture.html: one file, no network needed, opens in any browser. Verified end to end on the re:Imburse demo (see references/make-diagram-example.py, a complete working generator).
Pick the right diagram skill
| User wants | Skill |
|---|---|
| Nice looking page to open or share, polished presentation, "html", "no overlapping lines" | this skill |
| A PNG for slides or a PR | aws-diagram-png (awsdac) |
| Editable draw.io XML | aws-architecture-diagram |
If the user only says "diagram" and wants it to look good, default to this skill. All three must use real AWS icons.
Non negotiables
- Real AWS icons only. Never draw lookalike shapes or use emoji. If an icon is missing, find the right one (see below).
- No overlapping lines. Every connector is an orthogonal path (M, H, V commands only) that crosses no other connector, shares no segment with one, and passes through no card. This is enforced by
check_layout()in the example script, which must pass before the HTML is written. Do not remove it. - Look at the rendered result. Render with headless Chrome, read the screenshot, fix what is wrong. A passing checker is not enough (it cannot see a frame title hidden under a card, for example).
- No dashes as punctuation in any text on the page (use commas, colons, or split sentences). Compound words are fine.
- Only data flow services get cards and connectors. Cross cutting services (CloudWatch, X-Ray, CloudFormation or SAM, IAM) go in a separate panel below with no connectors, unless the user asks to draw them in the flow.
Getting the official icons
The AWS Architecture Icons deck is cached by awsdac (brew install awsdac). Run any awsdac render once to populate ~/.cache/awsdac/. That first run downloads the icon definition YAML (definition-for-aws-icons-light.yaml) and, from the Zip.Url field inside it, the full icon deck zip, extracted alongside it in the same cache directory.
What ships with it
1 file 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.
- today First seen · 84 lines · 83 tokens per session scan A 5d677e98cd1a
aws-diagram-html is a skill published in the GitHub repository seandkendall/kiro-config (8 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 1,982 once invoked, about $0.0003 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 2026-10-23.
Other skills, from other repositories
aws-cdk
AWS CDK infrastructure development in TypeScript. Use when creating stacks, constructs, L2/L3 patterns, CDK testing, synth/deploy pipelines or organizing IaC code.
aws-serverless
Building production-ready serverless applications on AWS. Use when working with Lambda, API Gateway, SQS, SNS, DynamoDB Streams, SAM/CDK deployment or optimizing cold starts.
aws-terraform
AWS infrastructure with Terraform. Use when creating modules, managing remote state, writing tftest.hcl tests, refactoring IaC or following HashiCorp style guide.
aws-architecture
AWS architecture decisions, serverless patterns, event-driven design, service boundaries and Well-Architected Framework. Use when designing system architecture or making infrastructure tradeoffs.
aws-lambda-python
AWS Lambda development with Python. Use when writing Lambda handlers, packaging with layers, using boto3/Powertools, structured logging or optimizing Python Lambda performance.
aws-security
AWS security implementation. Use when configuring IAM policies, managing secrets, setting up encryption, securing networking, hardening services or auditing configurations.