A task guide for creating and editing nifdi diagrams: structured pictures made from boxes, text, icons, and connecting lines. It covers architecture diagrams, flowcharts, and system or network diagrams.

Building diagrams from written descriptions or pictures, changing existing diagrams, and working with .nifdi.svg files.

It explains how to describe diagram structure and connections so the nifdi server can build and repair the layout.

nifdi — Skill for Claude Code by nifdi-app

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 nifdi-app/nifdi-plugin --skill nifdi

Clone the repo

git clone --depth 1 https://github.com/nifdi-app/nifdi-plugin

Made for: Claude Code.

Or install nifdi, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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/nifdi-app/nifdi-plugin/nifdi/github.svg)](https://agentmods.dev/skills/nifdi-app/nifdi-plugin/nifdi)

Your own site

<a href="https://agentmods.dev/skills/nifdi-app/nifdi-plugin/nifdi"><img src="https://agentmods.dev/badge/skills/nifdi-app/nifdi-plugin/nifdi/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nifdi-app/nifdi-plugin/nifdi"><img src="https://agentmods.dev/badge/skills/nifdi-app/nifdi-plugin/nifdi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,581 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.

Model	Per session	Once invoked
Fable 5.1	$0.00130	$0.01581
Opus 5	$0.00065	$0.00790
Sonnet 5	$0.00026	$0.00316
Haiku 4.5	$0.00013	$0.00158

Measured 9d ago against content hash 10421c698633, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nifdi 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 9d 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/nifdi/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building diagrams with nifdi

nifdi is a structured diagram editor: containers, text and icons, wired by paths. Reach for it when the picture is boxes and arrows. It is not a vector canvas — the server owns layout, and completes and repairs geometry rather than honouring pixel-exact composition. Fighting that is the single most expensive mistake available here.

The model in one screen

A diagram is a tree of blocks plus paths that wire them.

container — a box that holds other blocks. Nesting is containment: a <container> holds its children directly, and there is no nested <canvas>.
text — words.
icon — artwork, referenced by asset="library:name" (find one with search_icons) or asset="#asset-…" for artwork already in the diagram.
path — a connector between two blocks, wired through <from> and <to>.

Blocks carry pos="x y" and size="w h", both optional. Omitted geometry is completed by the server; a declared pos arranges blocks against one another rather than fixing canvas coordinates. Style is a <style> block of selector { property: value; } rules with nifdi's own semantic property names — not CSS.

<container id="vpc" size="400 240"><text place="on top-edge">Production VPC</text>
  <icon id="api" asset="aws:amazon-ec2"><text>API server</text></icon></container>

That fragment shows the two relationships that matter, and they are different:

<icon> is inside the container — containment. It lives in the box.
<text place="on top-edge"> is attached to the container — it is the box's title, riding its border, and it travels with the box.

The one rule to internalise: attach labels, never place them beside

Text sitting beside, above or below an icon in the picture you are recreating is that icon's label. A name across a container's top border is that container's attached child. Author both as nested elements naming a place — never as a sibling text block positioned next to the host.

Read the full file on GitHub · 112 lines

Files

What ships with it

5 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.

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.

9d ago First seen · 112 lines · 130 tokens per session scan A 10421c698633

Subscribe to this mod's changes

nifdi is a skill published in the GitHub repository nifdi-app/nifdi-plugin (0 stars, last pushed 16d ago), licensed Apache-2.0. It adds 130 tokens to every session and 1,581 once invoked, about $0.0006 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

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

nifdi