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 jnPiyush/AgentX --skill diagram-as-codegit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/diagram-as-code)<a href="https://agentmods.dev/skills/jnpiyush/agentx/diagram-as-code"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/diagram-as-code/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/jnpiyush/agentx/diagram-as-code"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/diagram-as-code.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 | $0.00085 | $0.01660 |
| Opus 5.5 | $0.00034 | $0.00664 |
| Sonnet 5.5 | $0.00017 | $0.00332 |
| Haiku 4.5 | $0.00009 | $0.00166 |
Grade A, and why
diagram-as-code 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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagrams as Code
Purpose: One conventions layer for all diagrams produced across Frontier roles. Principle: Text-first, diffable, reviewable, rendered at read-time. Binary formats (PNG, JPG, VSDX) are an export, never the source of truth. Scope: This skill is the convention layer. The
diagram-specialistsub-agent (.github/agents/internal/diagram-specialist.agent.md) owns spawn-and-execute behavior. Each reference file covers one format or quality concern.
When to Use
Load this skill any time an agent needs to:
- Create a swimlane / cross-functional workflow (e.g. the contract-lifecycle template)
- Draw a C4 context / container / component diagram for an ADR or spec
- Capture an API or event sequence
- Document a state machine or lifecycle
- Render an ER diagram or data model
- Produce a network / infra / pipeline topology
- Convert a legacy Visio file into a diffable code artifact
- Review an existing diagram for clarity and correctness
Default Format Policy (Mermaid-First)
Mermaid is the default for all Frontier templates and artifacts. It renders natively in GitHub, VS Code preview, most markdown tooling, and is the lowest-friction option for reviewers.
Use another format ONLY when one of these is true:
- Mermaid cannot express the diagram intent (e.g. true swimlanes with role columns, native Visio
.vsdxround-trip, complex cluster layouts). - The user explicitly asks for PlantUML, draw.io, Structurizr, or Graphviz.
- The artifact must round-trip to Visio (
.vsdx) -- in that case use draw.io.
When falling back, record the reason in the diagram's header comment (e.g. <!-- Format: draw.io; reason: Visio round-trip required -->).
Decision Matrix (pick-the-format)
| Intent | Primary format | Fallback (only if Mermaid cannot express it) | Visio round-trip |
|---|---|---|---|
| System context (C4 L1) / containers (C4 L2) | Mermaid C4 | Structurizr DSL | Mermaid -> Visio web |
| Component / class structure (C4 L3, UML) | Mermaid class / flowchart | PlantUML | draw.io |
| Sequence (API, message, handoff) | Mermaid sequence | PlantUML sequence | Mermaid -> Visio web |
| State machine / lifecycle | Mermaid state | PlantUML state | draw.io |
| ER / data model | Mermaid ER | PlantUML ER | draw.io |
| Journey map / capability map | Mermaid flowchart (LR) or journey | draw.io | Mermaid -> Visio web |
| Dependency / call graph | Mermaid flowchart | Graphviz DOT | SVG -> draw.io -> .vsdx |
| Gantt / roadmap timeline | Mermaid gantt | draw.io | draw.io |
| Cross-functional workflow / swimlane / RACI | Mermaid flowchart with subgraph lanes | PlantUML activity beta, then draw.io CFF | draw.io -> .vsdx |
| Role-phase matrix (roles as columns, phases as bands) | Mermaid flowchart with subgraph lanes | draw.io CFF | Native .vsdx export |
| Network / infra topology with many cluster boundaries | Mermaid flowchart with subgraphs | draw.io | Native .vsdx export |
What ships with it
7 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.
- 1mo ago Changed fce635a7e60e
- 1mo ago First seen · 112 lines · 85 tokens per session scan A 0f7c307896ff
diagram-as-code is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,660 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…