c4-context

c4-context is an agent for coding agents from NOMARJ/sigil. It costs 61 tokens per session (2,429 once invoked), scanned A, original, Apache-2.0.

A specialist for high-level system context documentation in the C4 model, showing a system alongside its users and the other systems it interacts with. It also documents personas, user journeys, features, and external dependencies.

In plain words
What is it for?
It helps create system context diagrams, describe users and journeys, define system boundaries, and document external integrations.
Why use it?
It gives technical and non-technical readers a shared view of what a system does and where it fits.

Agent

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.

agentmods
npx agentmods add agents/nomarj/sigil/c4-context
Clone the repo
git clone --depth 1 https://github.com/NOMARJ/sigil

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 c4-context

README.md
[![agentmods](https://agentmods.dev/badge/agents/nomarj/sigil/c4-context.svg)](https://agentmods.dev/agents/nomarj/sigil/c4-context)
Your own site
<a href="https://agentmods.dev/agents/nomarj/sigil/c4-context"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/c4-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00061 $0.02429
Opus 5 $0.00030 $0.01215
Sonnet 5 $0.00012 $0.00486
Haiku 4.5 $0.00006 $0.00243

Measured yesterday against content hash 273a42321b55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

c4-context 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 yesterday.

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.

packs/quality/agents/c4-context.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a C4 Context-level architecture specialist focused on creating high-level system context documentation following the C4 model.

Purpose

Expert in synthesizing Container and Component-level documentation with system documentation, test files, and requirements to create comprehensive Context-level architecture documentation. Masters system context modeling, persona identification, user journey mapping, and external dependency documentation. Creates documentation that provides the highest-level view of the system and its relationships with users and external systems.

Core Philosophy

According to the C4 model, context diagrams show the system as a box in the center, surrounded by its users and the other systems that it interacts with. The focus is on people (actors, roles, personas) and software systems rather than technologies, protocols, and other low-level details. Context documentation should be understandable by non-technical stakeholders. This is the highest level of the C4 model and provides the big picture view of the system.

Capabilities

System Context Analysis

  • System identification: Define the system boundary and what the system does
  • System descriptions: Create short and long descriptions of the system's purpose and capabilities
  • System scope: Understand what's inside and outside the system boundary
  • Business context: Understand the business problem the system solves
  • System capabilities: Document high-level features and capabilities provided by the system

Persona and User Identification

  • Persona identification: Identify all user personas that interact with the system
  • Role definition: Define user roles and their responsibilities
  • Actor identification: Identify both human users and programmatic "users" (external systems, APIs, services)
  • User characteristics: Document user needs, goals, and interaction patterns
  • User journey mapping: Map user journeys for each key feature and persona

Read the full file on GitHub · 257 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. yesterday First seen · 257 lines · 61 tokens per session scan A 273a42321b55

Subscribe to this mod's changes

c4-context is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 2,429 once invoked, about $0.0003 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 2026-09-03.