context-diagram

context-diagram is a skill for Claude Code from sethdford/claude-skills. It costs 30 tokens per session (582 once invoked), scanned A, original, MIT.

A high-level diagram of a software system and the people, services, and external systems that interact with it. It shows what belongs inside the system boundary and what remains outside.

In plain words
What is it for?
Use it when onboarding a team, clarifying system boundaries, or documenting connections to services such as payment, email, and storage providers.
Why use it?
It makes the system's scope, dependencies, users, and data exchanges easier for a team to understand.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the communication plugin — 7 skills shipped together

Good fit Use it when onboarding a team, clarifying system boundaries, or documenting connections to services such as payment, email, and storage providers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sethdford/claude-skills/context-diagram
Install

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.

Any agent
npx skills add sethdford/claude-skills --skill context-diagram
Clone the repo
git clone --depth 1 https://github.com/sethdford/claude-skills

Made for: Claude Code.

Or install communication, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

agentmods badge for context-diagram

README.md
[![agentmods](https://agentmods.dev/badge/skills/sethdford/claude-skills/context-diagram/github.svg)](https://agentmods.dev/skills/sethdford/claude-skills/context-diagram)
Your own site
<a href="https://agentmods.dev/skills/sethdford/claude-skills/context-diagram"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/context-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.

agentmods 80×15 button for context-diagram

Your own site · 80×15
<a href="https://agentmods.dev/skills/sethdford/claude-skills/context-diagram"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/context-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00582
Opus 5 $0.00015 $0.00291
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 11d ago against content hash a5733eb41834, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

context-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.

architect/communication/skills/context-diagram/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Diagram

Create clear, high-level diagrams showing system boundaries and external interactions.

Context

You are creating context diagrams to establish system scope. Show what's inside vs outside. Identify external dependencies and user interactions. Read system requirements and interfaces.

Domain Context

Based on C4 model and systems thinking:

  • System Boundary: What's included? Often misaligned between teams. Clear boundary prevents scope creep.
  • External Systems: Payment processors, email services, third-party APIs. Owned by others; you depend on them.
  • Users/Actors: Who uses the system? Customers, admins, automated systems. Different users have different interaction patterns.
  • Data Flows: What data crosses the boundary? In what direction? Frequency? Synchronous or asynchronous?

Instructions

  1. Draw Central Rectangle: This is "your system" (e.g., "E-commerce Platform").

  2. Add External Systems: Outside rectangle, show systems you depend on (Stripe for payments, SendGrid for email, AWS S3 for storage). Label communication protocol (REST, webhook, batch).

  3. Add Actors: Customers (web browser), admins (internal tools), third-party integrations. Arrows show interaction direction and protocol.

  4. Label Data Flows:

    • "Customer → Platform: Order request (REST, JSON)"
    • "Platform → Stripe: Payment (REST, HTTPS)"
    • "Platform → Email Service: Confirmation (REST, webhook)"
  5. Keep Simple: One diagram, not multi-level. Aim for ~5-10 external entities. More = split into smaller diagrams or go to container level.

Anti-Patterns

  • Too Detailed: Show internal components in context diagram. Result: defeats purpose of high-level view. Guard: Only show external systems and major actors.
  • Unclear Boundaries: "Is authentication part of the system?" Result: confusion. Guard: Explicitly define what's in/out. If shared, explain ownership.
  • No Data Flow Labels: Assume readers know what data flows. Result: ambiguity. Guard: Label every arrow: "Customer data (GDPR-sensitive)", "Metrics (non-sensitive)".
  • Outdated Diagram: New external integration added, diagram not updated. Result: wrong mental model. Guard: Update when external dependencies change; periodic review.

Read the full file on GitHub · 50 lines

Changes

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.

  1. 11d ago First seen · 50 lines · 30 tokens per session scan A a5733eb41834

Subscribe to this mod's changes

context-diagram is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 582 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.

Related

Other skills, from other repositories