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 topprismdata/cultivating-ml-agent --skill okf-visualize-knowledgegit clone --depth 1 https://github.com/topprismdata/cultivating-ml-agentWrote 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/topprismdata/cultivating-ml-agent/okf-visualize-knowledge)<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/okf-visualize-knowledge"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/okf-visualize-knowledge.svg" alt="Measured on agentmods" 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 | $0.00128 | $0.01501 |
| Opus 5 | $0.00064 | $0.00750 |
| Sonnet 5 | $0.00026 | $0.00300 |
| Haiku 4.5 | $0.00013 | $0.00150 |
Grade A, and why
okf-visualize-knowledge 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 7d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKF Visualize Knowledge
Problem
Knowledge bases grow organically as folders of markdown files with cross-references. Without visualization:
- Hard to spot which concepts are isolated (zero cross-refs)
- Hard to see which skills have the most evidence
- Hard to communicate "here's what I know" to teammates
- Manual diagrams are stale the moment you write them
Reality: A 5-second command turns your notes into an interactive graph.
Context / Trigger Conditions
Use this skill when:
- You have a directory of
.mdfiles with at least one cross-link ([text](other.md)) - The files have a consistent organization (subdirectories, or flat)
- You want to audit which concepts are orphans
- You want a shareable, offline HTML view
Don't use:
- Single-file notes (no cross-refs → no graph)
- Confidential knowledge (the HTML has all content embedded)
Solution: 5-Minute Pipeline
Step 1: Install OKF tools
git clone https://github.com/GoogleCloudPlatform/knowledge-catalog.git
cd knowledge-catalog/okf
pip install -e . # installs enrichment-agent CLI
Step 2: Add YAML frontmatter (optional but recommended)
Without frontmatter, OKF treats every file as a "Document" with no type. Add minimal frontmatter:
---
type: Skill
title: My Skill Name
description: One-line summary.
tags: [skill, kaggle]
timestamp: 2026-06-17T00:00:00Z
---
# My Skill
Body text with [cross-links](other-file.md)...
Step 3: Add index.md to each subdirectory (optional)
Each subdirectory gets a hub page:
---
type: Index
title: Subdir Name
description: What lives here.
---
# Subdir Name
* [file-one](file-one.md)
* [file-two](file-two.md)
Step 4: Run visualize
enrichment-agent visualize \
--bundle /path/to/your/notes \
--out /tmp/my-graph.html
Output: a self-contained HTML file (~50 KB) you can open or share.
Step 5: Iterate
Add a new concept → re-run visualize → see how the graph grew. Orphan concepts (no cross-refs) become obvious in the graph — fix them by adding links.
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.
- 7d ago First seen · 176 lines · 128 tokens per session scan A b44bc721b4c4
okf-visualize-knowledge is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 10d ago), licensed MIT. It adds 128 tokens to every session and 1,501 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.
Other skills, from other repositories
huggingface-hub
Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
ws-ckpt
A Linux-only tool for creating and managing workspace snapshots. A snapshot is a saved view of files that can later be compared, restored, listed, or deleted.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.