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 karsten-s-nielsen/mad-scientist-skills --skill c4git clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-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/karsten-s-nielsen/mad-scientist-skills/c4)<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/c4"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/c4/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/karsten-s-nielsen/mad-scientist-skills/c4"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/c4.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 | $0.00171 | $0.11640 |
| Opus 5 | $0.00086 | $0.05820 |
| Sonnet 5 | $0.00034 | $0.02328 |
| Haiku 4.5 | $0.00017 | $0.01164 |
Grade B, and why
c4 scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Linux (Debian/Ubuntu) | `sudo apt install openjdk-21-jre` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
WAR_URL=$(curl -s https://docs.structurizr.com/binaries | grep -oP 'https://download\.structurizr\.com/structurizr-[0-9.]+\.war' | head -1) How it starts
The opening of the file, as written. The whole thing — 954 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C4 Architecture Diagram Builder
A C4 diagram is a self-contained HTML file that visualizes software architecture at multiple zoom levels using the C4 model. This skill uses Structurizr DSL — the official C4 model notation created by Simon Brown — as the source language. Diagrams are rendered locally via a two-stage pipeline: Structurizr exports DSL to PlantUML C4, then plantuml.jar renders SVGs. SVGs are embedded directly in the HTML — making the output fully self-contained and offline-capable.
Why Structurizr DSL?
- Official format — Structurizr DSL is the canonical C4 authoring language by the creator of C4
- Model-first — Define the model once, create multiple views from it (no duplication)
- Portable — DSL files can be imported into Structurizr tools and other C4-compatible software
- Cleaner syntax — No
@startuml/@endumlwrappers or!includedirectives
When to use this skill
When the user asks for:
- Architecture diagrams or system diagrams
- C4 model diagrams (Context, Container, Component)
- Software structure visualization
- "How does this system fit together?"
- Deployment or dynamic interaction diagrams
- Codebase architecture overview
How to use this skill
- Understand the system. Read relevant code, configs, and docs to understand the architecture. If the user describes a system verbally, capture the key elements.
- Identify the diagram type from the user's request.
- Load the matching template from
templates/:templates/system-context.md— Level 1: People, systems, and high-level interactionstemplates/container.md— Level 2: Applications, data stores, and their communicationtemplates/component.md— Level 3: Internal structure of a single containertemplates/dynamic.md— Numbered interaction sequences between elementstemplates/deployment.md— Infrastructure nodes and deployed containers
- If no specific level requested, build a multi-level explorer that includes System Context + Container diagrams with tab switching.
- Generate Structurizr DSL source for each diagram level following the template syntax.
- Render each diagram locally via the two-stage pipeline (see rendering workflow below).
- Assemble the HTML file with embedded SVGs, tabbed navigation, DSL panel, and copy button.
- Save the
.dslsource file alongside the HTML for version control. - Open in browser. After writing the HTML file, run
open <filename>.html(macOS) orstart <filename>.html(Windows) to launch it.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 954 lines · 171 tokens per session scan B 05cb5c9063de
c4 is a skill published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 171 tokens to every session and 11,640 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-front-design
Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.
recipe-front-adjust
Adjust an already-implemented UI in-session with verification against the design source.
fidelity-gate
Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.
a11y-audit
Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…
design-review
UI/UX design consistency audit. Code-based DX1-DX20 checklist covering states, consistency, accessibility, responsive behavior, and interaction patterns. Optional visual audit via chrome-devtools screenshots and automated WCAG accessibility via axe-core. DAP1-DAP12 anti-pattern detection. Modes: [path], visual…
design
Intent-first UI design with conscious, traceable design decisions. Persists decisions in .interface-design/ for cross-session consistency. Includes domain exploration, design system generation (system.md + system.json), per-component construction with mandatory checkpoints, and craft validation tests. Modes: init…