loadout likec4.instructions.md

Instructions for writing LikeC4 files, a text-based way to describe software architecture and generate C4 diagrams. C4 diagrams show systems, their major parts, and how those parts connect.

In plain words
What is it for?
Use it to model system, container, and component views, define relationships and styles, or maintain multi-file architecture models.
Why use it?
It keeps architecture descriptions and diagrams consistent and easier to validate as the system changes.

Instructions file for GitHub Copilot

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 instructions/stefaniuk/loadout/likec4
Clone the repo
git clone --depth 1 https://github.com/stefaniuk/loadout

Made for: GitHub Copilot.

Per session 1,440 This file is loaded in full into every session.
When invoked 1,440 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01440 $0.01440
Opus 5 $0.00720 $0.00720
Sonnet 5 $0.00288 $0.00288
Haiku 4.5 $0.00144 $0.00144

Measured yesterday against content hash 230e26ee673e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loadout likec4.instructions.md 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.

.github/instructions/likec4.instructions.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LikeC4 DSL Instructions (architecture-as-code diagrams) 📐

These instructions define the engineering approach for authoring LikeC4 architecture-as-code files.

They must remain applicable to:

  • C4 model definitions (system context, container, component diagrams)
  • Specification blocks (element kinds, relationship kinds, styles)
  • View definitions and layout
  • Multi-file workspace models

They are non-negotiable unless an exception is explicitly documented (with rationale and expiry) in an ADR/decision record.

Cross-references. For architecture documentation standards, see architecture-baseline.include.md. For the C4 model generation prompt, see architecture.05-c4-model.prompt.md. This file focuses exclusively on LikeC4 DSL patterns and validation.

Identifier scheme. Every normative rule carries a unique tag in the form [LC4-<prefix>-NNN], where the prefix maps to the containing section (for example QR for Quick Reference, OP for Operating Principles, SYN for Syntax, VAL for Validation, STY for Style). Use these identifiers when referencing, planning, or validating requirements.


0. Quick reference (apply first) 🧠

This section exists so humans and AI assistants can reliably apply the most important rules even when context is tight.

  • [LC4-QR-001] Element syntax: use identifier = kind 'Title' - identifier first, then =, then kind.
  • [LC4-QR-002] Never mix forms: kind identifier = 'Title' is INVALID and silently drops the element.
  • [LC4-QR-003] Validate after generation: use LikeC4 MCP tools to confirm all elements parsed correctly.
  • [LC4-QR-004] Specification first: declare every element kind in specification {} before using it in model {}.

1. Operating principles 🧭

These principles extend constitution.md §3.

  • [LC4-OP-001] Treat the specification as the source of truth for the architecture model. If a system, container, or component is not evidenced in the codebase, it does not belong in the diagram.
  • [LC4-OP-002] Prefer small, incremental updates over full model rewrites.
  • [LC4-OP-003] Design for determinism: the same model source must produce the same diagrams.
  • [LC4-OP-004] Validate every change using LikeC4 MCP tools - the tooling fails silently on syntax errors.

Read the full file on GitHub · 147 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 · 147 lines · 1,440 tokens per session scan A 230e26ee673e

Subscribe to this mod's changes

loadout likec4.instructions.md is an instructions file published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 3d ago), licensed MIT. It adds 1,440 tokens to every session, about $0.0072 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 2026-08-31.