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 xSAVIKx/okf-skills --skill okf-vizgit clone --depth 1 https://github.com/xSAVIKx/okf-skillsWrote 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/xsavikx/okf-skills/okf-viz)<a href="https://agentmods.dev/skills/xsavikx/okf-skills/okf-viz"><img src="https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-viz/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/xsavikx/okf-skills/okf-viz"><img src="https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-viz.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 | $0.00088 | $0.00802 |
| Opus 5 | $0.00044 | $0.00401 |
| Sonnet 5 | $0.00018 | $0.00160 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
okf-viz 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okf-viz — OKF Bundle Visualizer
Renders any OKF bundle into one self-contained interactive index.html beside
index.md: a three-pane explorer with a Cytoscape graph (switchable layouts),
a navigator (tree + type/tag filters + search), and a rendered concept reader.
Setup
# Install the published binary (Go 1.24+) — no clone needed:
go install github.com/xSAVIKx/okf-skills/skills/[email protected]
# …or build from a clone of the repository:
cd skills/okf-viz && go build -o okf-viz .
Commands
render
./okf-viz render --bundle <bundle-dir> [--out <file>] [--offline] [--theme system|light|dark] [--lang en] [--title <text>]
--bundle(required): the OKF bundle to visualize.--out: output path; default<bundle>/index.html.--offline: inline the graph library for a fully isolated file (no CDN).--theme: initial theme (defaultsystem, follows the OS); switchable in-page.--lang: UI-chrome language (defaulten).--title: page title (default derived from the bundle).--inline-all: always inline every concept body into the single file, regardless of size (the archival/shareable form).--threshold: concept count above which bodies are written lazily as sibling_okf/<id>.htmlfragments instead of inlined (default 150). Small bundles stay a single self-contained file; large bundles load a concept's body on selection. Re-running produces byte-identicalindex.htmland fragments. In-page, ER toggles the entity-relationship view and Cluster collapses directories into tappable super-nodes for large graphs.--diff <bundle>: highlight what changed versus another bundle revision — added / removed / changed concepts and edges, using each concept'scontent_hash(body-comparison fallback when a hash is absent). Deterministic and byte-stable.--bundles <a,b,…>: federate additional bundles into one view; each bundle's node IDs are namespaced so identical IDs across bundles stay distinct. Single-bundle output is unchanged.- In-page, Coverage recolors nodes by enrichment state, and PNG / JSON export the graph and the visible subgraph. The three panes carry ARIA roles and the graph is keyboard-traversable (focus it, then arrow between neighbors, Enter to select).
What ships with it
34 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.
- assets/app.css 3.6 KB
- assets/app.js 29 KB runs code
- assets/page.tmpl.html 2.9 KB
- assets/vendor/cola.min.js 78 KB runs code
- assets/vendor/cose-base.min.js 44 KB runs code
- assets/vendor/cytoscape-cola.min.js 8.1 KB runs code
- assets/vendor/cytoscape-dagre.min.js 4.4 KB runs code
- assets/vendor/cytoscape-fcose.min.js 20 KB runs code
- assets/vendor/cytoscape.min.js 365 KB runs code
- assets/vendor/dagre.min.js 277 KB runs code
- assets/vendor/layout-base.min.js 58 KB runs code
- assets/vendor/LICENSES.md 2.7 KB
- cdn.go 1.6 KB
- CHANGELOG.md 2.7 KB
- go.mod 243 B
- go.sum 1.4 KB
- integrate_test.go 2.2 KB
- integrate.go 4.6 KB
- links_test.go 4.0 KB
- links.go 4.4 KB
- main.go 6.0 KB
- model_test.go 959 B
- model.go 5.9 KB
- okf-viz 8006 KB
- render_test.go 7.8 KB
- render.go 11 KB
- schema_test.go 859 B
- schema.go 2.6 KB
- testdata/linked/index.md 34 B
- testdata/linked/tables/customers.md 151 B
- testdata/linked/tables/orders.md 270 B
- testdata/linkless/index.md 42 B
- testdata/linkless/notes/a.md 63 B
- testdata/linkless/notes/b.md 64 B
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.
- 12d ago First seen · 55 lines · 88 tokens per session scan A d8a4838a08ae
okf-viz is a skill published in the GitHub repository xSAVIKx/okf-skills (33 stars, last pushed 12d ago), licensed Apache-2.0. It adds 88 tokens to every session and 802 once invoked, about $0.0004 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.
Other skills, from other repositories
okf-authoring
Author Open Knowledge Format (OKF) bundles — knowledge represented as a directory of markdown files with YAML frontmatter. Use when asked to create, write, generate, enrich, or validate an OKF bundle or OKF concept docs; to turn a data source (Glue database, API, database, catalog), documentation, or a research topic…
report-authoring
The report-authoring methodology: required structure, language, evidence discipline, and figure selection. Read BEFORE your first createreport of a conversation - the tool validates shape; this is everything it cannot check.
okf-open-knowledge-format
Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert…
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…
astro-sites-manager
Comprehensive skill for building, migrating, and maintaining Astro v7 projects. Covers best practices from the official AGENTS.md, the v6→v7 migration path, validation of breaking/deprecated patterns, AI-enhanced dev server usage (background mode, JSON logging), advanced routing with src/fetch.ts, route caching…
paper2html
Convert an academic paper PDF into a publish-ready, self-contained single-page project homepage (a self-contained index.html) — the kind of paper landing page researchers host on GitHub Pages. Triggers when the user says "turn a paper into a project page/webpage", "paper2html", "generate a paper landing page / project…