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 odere-pro/claude-aws-architect --skill aws-layered-diagramgit clone --depth 1 https://github.com/odere-pro/claude-aws-architectWrote 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/odere-pro/claude-aws-architect/aws-layered-diagram)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-layered-diagram"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-layered-diagram/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/odere-pro/claude-aws-architect/aws-layered-diagram"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-layered-diagram.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 | $0.00075 | $0.01568 |
| Opus 5 | $0.00037 | $0.00784 |
| Sonnet 5 | $0.00015 | $0.00314 |
| Haiku 4.5 | $0.00007 | $0.00157 |
Grade A, and why
aws-layered-diagram 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 11d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Apply this skill any time an agent writes, edits, or reviews the per-feature diagrams.d2 file. The solution-architect agent emits this file at design time alongside design.md and the per-component contracts. Reviewers lint it before the design transitions from draft to accepted.
Trigger conditions:
- The agent is creating a new
diagrams.d2at the feature root. - The agent is adding a new container to the design and needs to add a matching
c4-l3-<container>layer. - The agent is editing an existing diagram and needs to confirm no top-level node is untagged.
- The agent is checking that every component named in
design.mdappears in thec4-l2layer. - The agent is performing a pre-acceptance review and needs to lint the diagram against all six required tags.
Procedure
- Place the file at the canonical path.
.claude/specs/<feature>/diagrams.d2. One file per feature; multiple components share the same file via layer tags. If creating, useassets/diagrams.d2.tmplas the starting structure. - Declare every required layer. The file must contain six layer tags:
c4-l1,c4-l2, onec4-l3-<container>per L2 container,seq-system,seq-component,seq-error. Missing any of the six is a lint failure. Detail inreferences/layer-taxonomy.md. - Tag every top-level node. No node at the file's top level may be untagged. Each node belongs to at least one layer; the lint enumerates top-level shapes and asserts every one carries a layer tag. Untagged top-level nodes are a lint failure.
- Resolve C4 levels consistently. L1 = system context (one box for the system, surrounding actors and external systems). L2 = containers (the major runtime/process boundaries inside the system). L3 = components within a single container (one diagram per L2 container). Detail in
references/c4-and-sequence.md. - Fill the three sequence layers.
seq-systemshows the canonical happy-path interaction across the L1 boundary;seq-componentshows a representative request handled inside a single L2 container;seq-errorshows the dominant failure mode and the recovery path. - Detect orphans. A node with no edges in or out, in any layer, is an orphan and is a lint failure. There are no exceptions: the central system node at
c4-l1must connect to its actors, every external actor must connect to the system, every container atc4-l2must connect to at least one peer, every component at L3 must connect to at least one sibling. Detail inreferences/layer-taxonomy.md.
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.
- 11d ago First seen · 63 lines · 75 tokens per session scan A dad017e12460
aws-layered-diagram is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,568 once invoked, about $0.0004 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 skills, from other repositories
design-taste-frontend
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
ui-refactor
Tactical user interface design guide for fixing layouts, selecting colors/fonts, and creating professional UIs. Use when the user asks to "make this look better," needs help with CSS/styling decisions, wants to create a design system, or needs to fix a cluttered interface.
ux-design
This skill should be used when the user mentions keywords related to ux-design.
design-sync
Sync DESIGN.md with your Figma design library — auto-update colors, typography, spacing, and component tokens.