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 decodingai-magazine/building-a-coding-agent-from-scratch-course --skill demo-6-article-kggit clone --depth 1 https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-courseWrote 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/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-6-article-kg)<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-6-article-kg"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-6-article-kg/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/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-6-article-kg"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/demo-6-article-kg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01861 |
| Opus 5.5 | $0.00024 | $0.00744 |
| Sonnet 5.5 | $0.00012 | $0.00372 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
demo-6-article-kg 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 1mo 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.
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.
The hardcore one: turn two live articles into a knowledge graph you can play with in the browser. You do all of it — you are the extractor (no NLP library) and you are the renderer (no graph library, no CDN, no framework). Two artifacts, one page that works the instant it lands.
Work the steps in order. Do not skip ahead to the HTML.
Step 0 — paths and plan
Both artifacts go in the output directory named in the Output default line at the very end of
these instructions — normally .decode/outputs/, but a destination the human named always wins.
Resolve it once, call it <OUT>, and use <OUT> everywhere below:
<OUT>/graph.json— the extraction<OUT>/kg.html— the page
Put the pipeline in todo_write as five items (fetch, extract, render, verify, report) and write
the real <OUT> path into the first one so you never re-derive it.
Step 1 — fetch the two sources
One web_fetch per URL (the tool returns Markdown):
- https://www.decodingai.com/p/understanding-neo4j-graph-agent-memory-system
- https://www.decodingai.com/p/ship-a-knowledge-graph-ontology-in-5-minutes
Keep the title and body prose. Ignore navigation, subscribe buttons, CTAs, comments, footers and trailing "read more" lists. If a fetch fails or comes back truncated, say so plainly and work with what you have — never invent content you did not fetch.
Step 2 — extract one merged graph
Distill ONE graph across both articles: an entity discussed in both articles is ONE node, not
two. Write it to <OUT>/graph.json:
{
"nodes": [
{
"id": "Ontology",
"type": "concept",
"desc": "one sentence in your own words"
},
{ "id": "Neo4j", "type": "tool", "desc": "one sentence in your own words" }
],
"edges": [{ "source": "Ontology", "target": "KG drift", "label": "prevents" }]
}
- 20–35 nodes. The key ideas, not every noun.
typeis exactly one ofconcept/tool/pattern/problem.descis one sentence of your own synthesis, not a quote.- Edges are directed;
labelis a short verb phrase (prevents,stores,queries). - Every
sourceandtargetmatches a nodeidexactly — ids are case-sensitive. - No orphans: every node has at least one edge.
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.
- 1mo ago First seen · 146 lines · 61 tokens per session scan A ba7f20a606d7
demo-6-article-kg is a skill published in the GitHub repository decodingai-magazine/building-a-coding-agent-from-scratch-course (1,034 stars, last pushed 5d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,861 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.