An authoring guide for C4 architecture diagrams, which show a system at three levels: its outside relationships, its runnable parts, and the major building blocks inside those parts. It uses C4-PlantUML notation in docs/architecture.md.

Use it to create or update C1–C3 sections of an architecture document during system design or when extracting architecture from an existing project.

It helps keep architecture diagrams at the right level of detail and avoids mixing system structure with code-level details.

c4-author — Skill for Claude Code and Codex by evolplus: An authoring guide for C4 architecture diagrams, which show…

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 skills/evolplus/talos/c4-author

Any agent

npx skills add evolplus/talos --skill c4-author

Clone the repo

git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Or install talos, the plugin that ships this one along with the rest of its 55 skills, 2 commands, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/evolplus/talos/c4-author.svg)](https://agentmods.dev/skills/evolplus/talos/c4-author)

Your own site

<a href="https://agentmods.dev/skills/evolplus/talos/c4-author"><img src="https://agentmods.dev/badge/skills/evolplus/talos/c4-author.svg" alt="Measured on agentmods" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,238 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00051	$0.02238
Opus 5	$0.00026	$0.01119
Sonnet 5	$0.00010	$0.00448
Haiku 4.5	$0.00005	$0.00224

Measured 3d ago against content hash abf2bdbe9afb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

c4-author 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 3d 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.

skills/c4-author/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C4 Author

When to use

You are the SA, authoring docs/architecture.md per architecture-template.md. The template prescribes the kit's adoption of the C4 model at levels C1 (Context), C2 (Containers), and C3 (Components). This skill gives you the notation conventions, per-level intent, and common pitfalls.

C4 level 4 (Code) is NOT in SA's scope. BE/FE Dev own it as an optional artifact per be-dev.md / fe-dev.md. This skill does not cover C4 Code.

What each level captures (and what each level is NOT)

Level	Captures	Does NOT capture
C1 Context	The system as ONE box. External actors (humans). External systems (other deployed software, in-org or third-party). High-level interactions ("validates session", "publishes events").	Internal structure. Don't decompose the system in C1.
C2 Containers	Deployable / runnable units inside the system boundary. Each container is something you'd start independently — a web app, a service, a database, a queue, a worker process, a file store.	Code-level structure. A container is not a class.
C3 Components	Major structural building blocks INSIDE one container. Logical groupings of related code — modules, packages, sets-of-classes. One C3 diagram per non-trivial container.	Individual classes or functions. If you find yourself drawing a class diagram, you're at C4 (out of scope).

The most common pitfall: conflating C2 and C3. A microservice is ALWAYS a C2 container (it's deployable). The handlers / domain services / infrastructure adapters INSIDE it are C3 components.

Notation — C4-PlantUML macros

The kit uses C4-PlantUML — a PlantUML library that adds C4-specific shapes and conventions. This matches the kit's existing PlantUML usage in frs-template.md sequence diagrams (same rendering pipeline; same markdown-reader support).

Three include directives, one per level:

Read the full file on GitHub · 109 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.

3d ago First seen · 109 lines · 51 tokens per session scan A abf2bdbe9afb

Subscribe to this mod's changes

c4-author is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 29d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,238 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 2026-08-31.

Design and UX Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens