What is interactive-widget?

A skill for adding actions that an AI model can call inside an interactive widget and for defining turn-based play. A widget is a small interactive interface embedded in another page or app.

Use it for games or other widgets where one or more models take turns, call documented actions, and work with saved widget state.

It connects model turns to the same shared actions used by the widget's human interface, so both can update the interaction consistently.

interactive-widget — Skill for Claude Code and Codex by googlicius

Install

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.

Any agent

npx skills add googlicius/obsidian-steward --skill interactive-widget

Clone the repo

git clone --depth 1 https://github.com/googlicius/obsidian-steward

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/googlicius/obsidian-steward/interactive-widget/github.svg)](https://agentmods.dev/skills/googlicius/obsidian-steward/interactive-widget)

Your own site

<a href="https://agentmods.dev/skills/googlicius/obsidian-steward/interactive-widget"><img src="https://agentmods.dev/badge/skills/googlicius/obsidian-steward/interactive-widget/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/googlicius/obsidian-steward/interactive-widget"><img src="https://agentmods.dev/badge/skills/googlicius/obsidian-steward/interactive-widget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,315 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Prompt Injection · line 35
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
medium Prompt Injection · line 94
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
medium Prompt Injection · line 106
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
medium Prompt Injection · line 108
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
medium Prompt Injection · line 111
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
medium Prompt Injection · line 115
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00037	$0.02315
Opus 5.5	$0.00015	$0.00926
Sonnet 5.5	$0.00007	$0.00463
Haiku 4.5	$0.00004	$0.00231

Measured 2mo ago against content hash df3425e4a569, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

interactive-widget 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 2mo 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.

standard-skills/widget/interactive-widget/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill after the stateful-widget skill when a widget should accept model turns (play vs AI, multi-model games, turn-ordered interaction).

When to use

User wants turn-ordered interaction with one or more model actors.
The widget already persists state (getState / setState) — see stateful-widget first.
You need host-dispatchable actions (registerAction) documented in Widget.md.

Skip for static widgets, user-only interactivity with no model turns, or SVG code mode.

Prerequisite workflow

Read stateful-widget → show_widget + working project with setState.
Then use this skill → registerAction in main.js (keep it last when split) + YAML fences in Widget.md.

Exposed actions (`main.js`)

Extract shared logic into action functions. User clicks and host dispatch call the same function. Register only actions models may invoke — not UI-only handlers (reset, local toggles).

API	Description
`window.stw.registerAction(name, fn)`	Expose an action the host can dispatch into the iframe. `name` must match a key under `actions` in `Widget.md`.
Handler return `{ ok: false, error }`	Invalid move; host surfaces `error` to the caller.
Handler return `{ ok: true, state? }`	Success; persist game state with `setState` inside the handler.

Rules:

fn receives params validated against the action's params spec in Widget.md.
User event handlers should call the same function the host will dispatch.
Do not registerAction for reset/restart — use a local button or window.stw.startNewSession() for "Play again".

Read the full file on GitHub · 241 lines

Changes

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.

2mo ago First seen · 241 lines · 37 tokens per session scan A df3425e4a569

Subscribe to this mod's changes

interactive-widget is a skill published in the GitHub repository googlicius/obsidian-steward (85 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 2,315 once invoked, about $0.0001 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.

Autonomous Agents Building agents obsidian-plugin shell terminal