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 sethdford/claude-skills --skill c4-model-diagramgit clone --depth 1 https://github.com/sethdford/claude-skillsWrote 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/sethdford/claude-skills/c4-model-diagram)<a href="https://agentmods.dev/skills/sethdford/claude-skills/c4-model-diagram"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/c4-model-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/sethdford/claude-skills/c4-model-diagram"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/c4-model-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 | $0.00036 | $0.00616 |
| Opus 5 | $0.00018 | $0.00308 |
| Sonnet 5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
c4-model-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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C4 Model Diagram
Create C4 diagrams to communicate architecture at multiple abstraction levels.
Context
You are creating architecture diagrams. Use C4 model for consistent representation. Start at highest level (context), zoom in progressively (container, component, code). Read architecture decisions and system structure.
Domain Context
Based on Simon Brown's C4 model:
- Context Diagram: System in environment. Shows external systems, users, data flows. Answers: "What is this system?"
- Container Diagram: Major building blocks (web app, database, API, message queue). Answers: "What's inside the system?"
- Component Diagram: Internal structure of container. Shows responsibilities, communication. Answers: "How is [container] organized?"
- Code Diagram: Class diagram for specific component. Shows classes, methods, relationships. Answers: "What does [component] contain?"
Instructions
-
Draw Context Diagram: Rectangle for your system. External systems (payment provider, email service). Actors (user, admin). Label data flows. Answers "What does this system do?"
-
Draw Container Diagram: Inside system rectangle, show containers (web app, API, database, cache). Interfaces between containers. Technology choices (PostgreSQL, Redis). Answers "What technology?"
-
Draw Component Diagram: Pick one container (API). Inside, show components (auth service, payment service, order service). Responsibilities, communication patterns.
-
Draw Code Diagram: For complex component, show classes, methods. Use standard UML or pseudo-code. Limit to critical logic; don't over-document.
-
Keep Diagrams Current: As architecture evolves, update diagrams. Outdated diagrams mislead teams. Use tools (draw.io, Structurizr, Miro) that allow collaboration and versioning.
Anti-Patterns
- One Massive Diagram: Try to show everything in one diagram. Result: unreadable, overwhelming. Guard: Use C4 levels; zoom progressively.
- Diagrams Without Legend: Assume readers know what symbols mean. Result: confusion. Guard: Label technologies, responsibilities, data flows clearly.
- Outdated Diagrams: Never update as system evolves. Result: teams follow wrong architecture. Guard: Update during architecture reviews; treat as living document.
- Too Much Detail Too Early: Start with code diagram. Result: lost in details before understanding system shape. Guard: Start at context; zoom in gradually; leave code diagram optional.
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 · 47 lines · 36 tokens per session scan A f6f3eebeaa68
c4-model-diagram is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 616 once invoked, about $0.0002 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
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize…
lead-intelligence
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, and personalized outreach. Use when the user wants to find, qualify, and reach high-value contacts.
team-builder
Interactive agent picker for composing and dispatching parallel teams.
cmd_aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
cmd_evolve
Cluster MEMORY.md entries by theme and optionally generate SKILL.md drafts.