Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/infographic-describer)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/infographic-describer"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/infographic-describer/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/openlinksoftware/ai-agent-skills/infographic-describer"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/infographic-describer.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 | $0.00108 | $0.01385 |
| Opus 5 | $0.00054 | $0.00692 |
| Sonnet 5 | $0.00022 | $0.00277 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade C, and why
infographic-describer scanned grade C 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 10d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sL "https://www.openlinksw.com/data/{directory}/" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL "https://www.openlinksw.com/data/{directory}/" | python3 -c " How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infographic Describer
Generate RDF-Turtle descriptions for files in a WebDAV-hosted directory using a SHACL shape as the property contract.
Workflow
Step 1: Discover Files
List the target WebDAV directory to enumerate files:
curl -sL "https://www.openlinksw.com/data/{directory}/" | python3 -c "
import sys, re
html = sys.stdin.read()
files = re.findall(r'title=\"File - ([^\"]+)\"', html)
for f in files:
print(f)
"
Classify by extension: .png → schema:ImageObject, .mp4 → schema:VideoObject, .html → schema:WebPage.
Step 2: Probe Describe Endpoint
Check which files have existing RDF data in the triplestore. Use the SPARQL DESCRIBE endpoint:
import urllib.parse, urllib.request
iri = f'https://www.openlinksw.com/DAV/www2.openlinksw.com/data/{directory}/{stem}.{ext}'
query = f'DESCRIBE <{iri}>'
url = 'http://www.openlinksw.com/sparql?query=' + urllib.parse.quote(query) + '&output=text%2Fn3'
req = urllib.request.Request(url, headers={'Accept': 'text/n3, */*'})
resp = urllib.request.urlopen(req, timeout=30)
data = resp.read().decode()
has_data = 'Empty' not in data and len(data.strip()) > 50
Step 3: Probe Thumbnails
Check for thumbnails using the content-explorer pattern:
https://www.openlinksw.com/data/content-explorer/thumbnails/{category}-{stem}.avif
Where {category} is the directory name (e.g., infographics). Probe with HTTP HEAD:
curl -sL -o /dev/null -w "%{http_code}" "$url"
Only files with 200 have thumbnails.
Step 4: Generate Descriptions
For each file, construct RDF triples using the SHACL shape properties:
| Property | Source | Fallback |
|---|---|---|
rdf:type |
File extension | schema:CreativeWork |
schema:name |
Filename stem (underscores/hyphens → spaces) | — |
schema:description |
Derived from name or describe page | "Infographic: {name}" |
schema:encodingFormat |
Content type from listing | Map extension to MIME |
schema:contentUrl |
Full DAV URL | — |
schema:thumbnailUrl |
Probe result (only if 200) | Omit |
schema:category |
Directory-based category IRI | Default to #Infographic |
wdrs:describedby |
Constructed describe endpoint URL | — |
schema:dateCreated |
Describe page (if available) | Omit |
schema:dateModified |
Describe page (if available) | Omit |
What ships with it
3 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.
- 10d ago First seen · 146 lines · 108 tokens per session scan C 494915c4827c
infographic-describer is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 1,385 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…