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 arkgum/arkgum-agent-skills --skill arkgum-research-to-pagegit clone --depth 1 https://github.com/arkgum/arkgum-agent-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/arkgum/arkgum-agent-skills/arkgum-research-to-page)<a href="https://agentmods.dev/skills/arkgum/arkgum-agent-skills/arkgum-research-to-page"><img src="https://agentmods.dev/badge/skills/arkgum/arkgum-agent-skills/arkgum-research-to-page/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/arkgum/arkgum-agent-skills/arkgum-research-to-page"><img src="https://agentmods.dev/badge/skills/arkgum/arkgum-agent-skills/arkgum-research-to-page.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 | $0.00139 | $0.01954 |
| Opus 5 | $0.00069 | $0.00977 |
| Sonnet 5 | $0.00028 | $0.00391 |
| Haiku 4.5 | $0.00014 | $0.00195 |
Grade A, and why
arkgum-research-to-page 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arkgum Research to Page
Turn one topic into a grounded page-building package. Own the NotebookLM work end to end; do not make the user shuttle prompts, sources, or answers between services.
Operating contract
- Use the configured NotebookLM MCP as the primary execution layer.
- Treat invocation as authorization to create one task-specific notebook, add task-relevant sources, run research, query the notebook, and write local run artifacts.
- Do not delete, rename, share, publish, or change access to notebooks without an explicit request.
- Never ask the user to open NotebookLM, paste prompts, import sources, or copy results as part of the normal flow.
- Ask the user to intervene only when Google authentication is missing or an external side effect needs separate authorization.
- Keep NotebookLM outputs and local artifacts in Russian unless the user requests another language. Preserve source titles, URLs, and quoted text in their original language.
- Ground factual claims in imported sources. Mark inference, uncertainty, missing evidence, and conflicting sources explicitly.
- Do not invent keyword volume, competition, traffic, rankings, testimonials, statistics, pricing, or product capabilities.
- Never expose cookies, tokens, session data, or other credentials in output or saved artifacts.
Load resources
Resolve <skill-root> as the directory containing this SKILL.md, then read:
<skill-root>/references/notebooklm-routing.mdbefore any NotebookLM action;<skill-root>/references/prompts.mdbefore querying NotebookLM;<skill-root>/references/output-contract.mdbefore writing artifacts or running QA.
Inputs and defaults
Required input: a research topic.
Use conversation context to infer optional inputs:
- audience and market/region;
- page goal and conversion action;
- offer, product, or resource being presented;
- user-provided sources or an existing notebook ID/URL;
- target builder and output language.
Defaults:
- research mode:
deepon the web; - output language: Russian;
- builder: Google AI Studio Build;
- page type: evidence-led landing page;
- missing offer or CTA: keep an explicit placeholder instead of inventing one;
- missing audience: infer a narrow likely audience and record that it is an assumption.
What ships with it
6 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.
- 12d ago First seen · 194 lines · 139 tokens per session scan A 7636b5d90312
arkgum-research-to-page is a skill published in the GitHub repository arkgum/arkgum-agent-skills (2 stars, last pushed 28d ago), licensed MIT. It adds 139 tokens to every session and 1,954 once invoked, about $0.0007 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
skills-manager-cli
Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…
ppt-design-skill
Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.
cesiumjs-camera
CesiumJS camera control - Camera, flyTo, lookAt, setView, ScreenSpaceCameraController, CameraEventAggregator, flight animation. Use when positioning the camera, creating flyTo animations, constraining user navigation, tracking entities, or converting between screen and world coordinates.
cesiumjs-custom-shader
CustomShader authoring — vertexShaderText and fragmentShaderText against VertexInput, FragmentInput, FeatureIds, Metadata, czmmodelMaterial. Use when reading EXTmeshfeatures or EXTstructuralmetadata property textures/tables, vertex displacement, or shading VoxelPrimitive.
cesiumjs-primitives
CesiumJS primitives and geometry - Primitive, GeometryInstance, Appearance, BufferPrimitive collections, GeoJsonPrimitive, Billboard/Label/PointPrimitive collections, built-in geometry shapes, ground primitives, classification. Use when rendering performance-critical static or vector geometry, loading GeoJSON without…
cesiumjs-time-properties
CesiumJS time, properties, and animation - Clock, JulianDate, TimeInterval, Property, SampledProperty, CallbackProperty, PathMode, interval and sampled path materials, interpolation, splines, CZML temporal data. Use when making entity attributes or path materials time-dynamic, configuring the simulation clock…