agentmods.dev

plantuml-validate

plantuml-validate is a skill for Claude Code from artem-from-ua/claude-plugins. It costs 45 tokens per session (841 once invoked), scanned A, original, MIT.

A checker for PlantUML diagrams embedded in Markdown files. It compares each diagram's source code with its generated diagram URL.

In plain words
What is it for?
Use it to check documentation before committing changes and to identify or repair missing or outdated PlantUML images.
Why use it?
It finds diagrams whose displayed image is missing or no longer matches the source code. It can also offer to update the affected URLs.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the plantuml plugin — 3 skills shipped together

not rated 11repo changed yesterday A scan 45 tokens original MIT

Good fit Use it to check documentation before committing changes and to identify or repair missing or outdated PlantUML images.

Compare 6 skills from other repositories ↓
View source ↗ artem-from-ua/claude-plugins
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add artem-from-ua/claude-plugins
Claude Code
/plugin install plantuml

Made for: Claude Code.

Or install plantuml, the plugin that ships this one along with the rest of its 3 skills.

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 plantuml-validate

README.md
[![agentmods](https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/plantuml-validate/github.svg)](https://agentmods.dev/skills/artem-from-ua/claude-plugins/plantuml-validate)
Your own site
<a href="https://agentmods.dev/skills/artem-from-ua/claude-plugins/plantuml-validate"><img src="https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/plantuml-validate/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.

agentmods 80×15 button for plantuml-validate

Your own site · 80×15
<a href="https://agentmods.dev/skills/artem-from-ua/claude-plugins/plantuml-validate"><img src="https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/plantuml-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00841
Opus 5 $0.00023 $0.00420
Sonnet 5 $0.00009 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured yesterday against content hash 14c3f7125c9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

plantuml-validate 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.

plugins/plantuml/commands/plantuml-validate/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PlantUML Validate

Validate that all PlantUML diagrams in markdown files are in sync with their source blocks and still render without complaints.

Three kinds of problem are detected:

  • Stale or missing URL — the image URL no longer encodes the source block. Auto-fixable with --sync.
  • Deprecated syntax or render error — the source renders with a warning box or fails to parse. Not auto-fixable: the source block has to be corrected by hand, then re-synced.
  • A diagram the tool cannot maintain — a <details> wrapper opened but not closed, or a fence indented inside a list or a blockquote. These are reported and left untouched, because rewriting them would guess at what the author meant. Not auto-fixable: close the wrapper, or move the diagram to the top level of the document, then re-sync.

Instructions

  1. Find all .md files in the project that contain PlantUML code blocks:

    grep -rl '```plantuml' . --include='*.md'

    This finds diagrams whether or not their source is collapsed: a collapsed diagram keeps its ordinary plantuml fence inside the <details> wrapper.

  2. Run the validation check on all found files:

    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/plantuml-encode.py" --check <files>

    CLAUDE_PLUGIN_ROOT is set automatically by Claude Code when running plugin commands.

    --check does both jobs: URL sync (offline) and render lint (asks the PlantUML server about each diagram). If the server is unreachable, the command prints a warning and reports only what it could verify — it does not fail. To check URL sync alone, put --no-lint before --check.

  3. Report results to the user:

    • If everything passes: confirm success with the file count, and say whether the render lint actually ran (the command's own output states this).
    • If issues were found: list each one with file, line number, and type — stale URL, missing URL, deprecated syntax / render error, or a diagram the tool cannot maintain.
    • Offer to auto-fix the URL problems. Do not offer to auto-fix deprecated syntax — show the server's message and the suggested replacement, and let the user decide what the diagram should say. Do not auto-fix an unmaintainable diagram either: say what has to move, and let the author move it.
    • Before a large fix, show --dry-run --sync <files> so the user can read the diff first.

Read the full file on GitHub · 52 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 Changed · +5 lines 14c3f7125c9e
  2. 2d ago Changed · +12 lines · +13 tokens per session 3bf4eb1e38c4
  3. 10d ago First seen · 35 lines · 32 tokens per session scan A 4a5a90538300

Subscribe to this mod's changes

plantuml-validate is a skill published in the GitHub repository artem-from-ua/claude-plugins (11 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 841 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens