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 rozek/wat-ai-broker --skill wat-referencegit clone --depth 1 https://github.com/rozek/wat-ai-brokerWrote 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/rozek/wat-ai-broker/wat-reference)<a href="https://agentmods.dev/skills/rozek/wat-ai-broker/wat-reference"><img src="https://agentmods.dev/badge/skills/rozek/wat-ai-broker/wat-reference/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/rozek/wat-ai-broker/wat-reference"><img src="https://agentmods.dev/badge/skills/rozek/wat-ai-broker/wat-reference.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 | $0.00052 | $0.03771 |
| Opus 5 | $0.00026 | $0.01886 |
| Sonnet 5 | $0.00010 | $0.00754 |
| Haiku 4.5 | $0.00005 | $0.00377 |
Grade A, and why
wat-reference 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebApp Tinkerer (WAT) — Data Model & Scripting Reference
Use this reference to write correct widget_add, widget_patch, configure, and script_set calls on the first try, without needing widget_get to look up property names.
Data model overview
Applet
├── Script
├── Behaviours (registered per category: "applet" | "page" | "widget")
├── Pages[] (ordered)
│ ├── Script
│ └── Widgets[] (ordered, index 0 = backmost)
│ └── Script
├── AppletOverlays[] (incl. Dialogs)
└── HeadExtensions
- every visual (applet, page, widget) may refer to a behaviour (a shared script for its category) and carry an individual script — the behaviour script always runs first
- widgets get their look & feel from their behaviour; the built-in widget behaviours wrap JavaScript-Code-Library (JCL) components
- exactly one page is the visited page (the one currently shown)
Addressing (WAT-AI-Broker)
| Parameter | Format |
|---|---|
page |
page name or 0-based page index |
widget |
widget name or 0-based widget index within its page |
target |
"applet" | page name | "page/widget" — used by script_get/script_set, error_report, configure, value_get/value_set, overlay_open/overlay_close |
category |
"applet" | "page" | "widget" — used by the behavior_* tools |
"applet" → the applet itself
"Home" → page named "Home"
"Home/Counter" → widget "Counter" on page "Home"
Visual properties
Shared by all visuals (applet, page, widget)
| Property | Type | Notes |
|---|---|---|
Name |
string | page names are unique, widget names should be |
Behavior |
string | null | full registered name incl. group prefix, e.g. "native_controls.Button" |
Script |
string | individual script source (see "pending script" below) |
FontFamily |
string | CSS font list |
FontSize |
number | px |
FontWeight |
100–900 | "normal" | "bold" |
|
FontStyle |
string | e.g. "italic" |
TextDecoration, TextShadow |
string | CSS |
TextAlignment |
"left" | "center" | "right" | "justify" |
|
LineHeight |
number | px |
Color |
string | foreground/text colour (CSS) |
BackgroundColor |
string | CSS |
BackgroundTexture |
string | image URL |
Opacity |
number | 0–100 (percent) |
Cursor |
string | standard CSS cursor names only |
Overflows |
string |
What ships with it
3 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.
- 7d ago First seen · 329 lines · 52 tokens per session scan A 8f876ee45aa6
wat-reference is a skill published in the GitHub repository rozek/wat-ai-broker (0 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 3,771 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…