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 aethrox/doctrine --skill architecture-diagramgit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/architecture-diagram)<a href="https://agentmods.dev/skills/aethrox/doctrine/architecture-diagram"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/architecture-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/aethrox/doctrine/architecture-diagram"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/architecture-diagram.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 | $0.00076 | $0.01202 |
| Opus 5 | $0.00038 | $0.00601 |
| Sonnet 5 | $0.00015 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
architecture-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 10d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Diagram
A diagram that tries to show everything at once tells a reader nothing; a diagram at the wrong zoom level either overwhelms a newcomer with detail or says nothing useful to someone who already knows the codebase. This skill's defining constraint, from Simon Brown's C4 model: pick the zoom level the audience actually needs before drawing anything, since context, container, component, and code answer different questions and mixing them in one diagram answers none of them well.
Phase 1: Find the mechanism and the level
Before touching a diagram tool, identify what a cold reader would otherwise have to assemble from prose: which parts talk to which, across what boundary, carrying what; or a decision or write path where a design principle hinges on a specific branch (an approval gate, a conflict check, a fallback). A diagram that draws every directory in the repo as a box is decoration, not documentation; skip it.
Then pick the C4 level that matches the question:
- Context: the system as one box, its users, and the other systems it talks to. For someone who has never seen this project before.
- Container: the major applications, services, APIs, and data stores that make up the system, and how they call each other. For someone about to work in the codebase.
- Component: how one container breaks down internally. For someone about to change that specific container.
- Code: classes and functions. Rarely worth a standing diagram; usually better left to the code itself and drawn ad hoc only when a specific structure needs explaining.
Most requests want Container; Context is for onboarding docs, Component is for a deep dive into one subsystem.
Phase 2: Draw with consistent notation
Boxes are the things (systems, containers, components); arrows are the relationships, each one labeled with what actually crosses it and its direction. A box without a label, or an arrow that just says "uses," is a placeholder, not a finished diagram. Use the project's own domain vocabulary for box names (see domain-modeling's ubiquitous language) rather than internal class or file names a reader outside the codebase would not recognize.
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.
- 10d ago First seen · 60 lines · 76 tokens per session scan A e2f6cc2cbb58
architecture-diagram is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 29d ago), licensed MIT. It adds 76 tokens to every session and 1,202 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 2026-08-30.
Other skills, from other repositories
flint-theme-author
Use when: creating, translating, refining, reviewing, or validating a custom Flint ThemeSpec from brand guidelines, websites, slide decks, publication references, design tokens, or an existing visual identity. Produce a reusable ThemeSpec JSON object for Flint Theme Lab without inventing fields or changing chart…
ce-polish
Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
umg-mcp-authoring
Use when Codex needs to create, edit, inspect, validate, or demo UE5.8 UMG interfaces through Unreal Motion Graphics MCP/FabUmgMcp, especially target/default workflows, widget tree authoring, HLSL-backed UI materials, Sequencer widget animations, Blueprint event wiring, readback validation, or operation-trace demo…
memoire-design-tooling
Use when a task spans interface understanding, design-system memory, UI audits, design CI, Figma, shadcn or Tailwind code generation, research, or agent design workflows and needs the correct Memi capability selected.
build-swiftui-interface
Use when a coding agent must design, scaffold, implement, or verify an iOS or macOS SwiftUI interface with Apple-platform state, accessibility, availability, testing, and Xcode evidence.