Borrowing it
Nothing to install: this file belongs to lukaisailovic/openislands. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lukaisailovic/openislands/main/.agents/skills/adding-new-islands/SKILL.mdgit clone --depth 1 https://github.com/lukaisailovic/openislandsWrote 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/lukaisailovic/openislands/adding-new-islands)<a href="https://agentmods.dev/skills/lukaisailovic/openislands/adding-new-islands"><img src="https://agentmods.dev/badge/skills/lukaisailovic/openislands/adding-new-islands/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/lukaisailovic/openislands/adding-new-islands"><img src="https://agentmods.dev/badge/skills/lukaisailovic/openislands/adding-new-islands.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 | $0.00146 | $0.02124 |
| Opus 5 | $0.00073 | $0.01062 |
| Sonnet 5 | $0.00029 | $0.00425 |
| Haiku 4.5 | $0.00015 | $0.00212 |
Grade A, and why
adding-new-islands 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 9d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a new island
An island is a stable, code-backed visual block with a typed config. An agent authors the
manifest by reading the island's schema and picking + configuring instances — it never writes
rendering code. So the schema and its .describe() copy ARE the product surface. Design the
interface first; the wiring is mechanical once the shape is right.
Before starting, read CONTRIBUTING.md ("Adding an island") and skim packages/schema/src/index.ts
to match the conventions of the nearest existing island. Always copy a sibling, not these
snippets — the real code is the source of truth.
Part 1 — Design the interface (do this before any code)
-
Name by intent, not by primitive. Convention is
<intent>.<form>(category.bar,waterfall.bars,correlation.scatter). The intent word must tell the agent when to pick this island and disambiguate it from neighbors — not describe the shape. Sanity-check the word for baggage:divergence.barswas chosen overdeviation.barsbecause "deviation" reads as standard deviation / error bars in a data context. -
Happy path = one line. Required fields are only those without which nothing renders (
dataset+ the bindings). Everything else is optional with a sensible default. An agent should get a working island from{ type, dataset, <bindings> }and refine from there. -
Make contradictory configs unrepresentable, not validated. If two knobs can conflict, collapse them into one. (For
divergence.barsa separatecolorsknob was dropped because a two-elementbucketsarray already expresses a custom two-tone — one path, no XOR to police.) -
Declarative only — no computation in config. Data shaping lives in SQL, never in the island. (
divergence.barshas nobaselinefield: diverge-from-target is avalue - targetsubtraction the author writes in SQL.) If you're tempted to add anoperation/formula/computefield, stop — that field belongs in the data layer.
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.
- 9d ago First seen · 129 lines · 146 tokens per session scan A 9d41afb34b98
adding-new-islands is a skill published in the GitHub repository lukaisailovic/openislands (21 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 2,124 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 2026-08-30.
Other skills, from other repositories
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
wiring-vizro-actions
Use this skill when adding cross-filter, cross-highlight, drill-through, or data export interactions to a Vizro dashboard — both for choosing the right interaction pattern during design and for implementing actions in code. Activate when the user wants clicks on a chart or table to filter or highlight other charts…
semiotic-charts
Build, repair, and verify charts in an existing Semiotic project, when Semiotic is explicitly requested, or when evaluating its documented capabilities against a visualization task. Preserve the project's dependency and runtime constraints; routine changes in another charting stack and tasks without a chart do not…
add-component
Add a new visualization component to Unovis end to end — the TypeScript core, the shared registry, the generated framework wrappers, a dev example, a gallery example, and docs. Use when asked to add/create a new component, chart type, plot, or diagram to the library, or to wire an existing core component through to…
add-gallery-example
Add an example to the Unovis gallery — a per-framework example directory under packages/shared/examples, registered in examples-list.tsx, with light/dark previews. Use when asked to add a gallery example, showcase a chart in the gallery, or create the gallery entry that accompanies a new component.
vs-project
Create Viking web projects, start and verify a local preview, or deploy a generated project to Volcengine IGA Pages when explicitly requested. Includes agent-guided feature, eligible application, dataset, scene, and authentication choices. Use only after confirming the installed CLI exposes vs project; otherwise stop…