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 agentmods add skills/wattdata/plugin/configurenpx skills add wattdata/plugin --skill configuregit clone --depth 1 https://github.com/wattdata/pluginWhat 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 | $0.00119 | $0.04277 |
| Opus 5 | $0.00060 | $0.02139 |
| Sonnet 5 | $0.00024 | $0.00855 |
| Haiku 4.5 | $0.00012 | $0.00428 |
Grade A, and why
configure scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Don't mistake a tool limit for a blocked download.** These download links are long, and an over-length URL can make Claude's default fetch tool fail for reasons that have nothing to do with the user's settings. So if t How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Watt
Purpose
/watt:configure is the user's setup and connectivity aide. It walks a new user through configuring Watt the first time — and it's the same place a returning user comes back to when something stops connecting. It settles their account type to tailor the path, checks the four things Watt needs, verifies the two it can verify, fixes whatever's off one step at a time, and leaves them able to use Watt.
Every beat ends able to use Watt — or holding the one exact next step to get there. When a check fails, hand over the precise move (the click, the admin link, or /watt:help) and wait on the user's signal; never retry blindly or guess past a step that isn't done — that just loops on a connection that isn't ready.
Works with
- Called by: the user (
/watt:configure), or any skill that hits a connection or authentication wall — this is the connect/recovery door the rest of the plugin points to. - Hands off to:
/watt:audience,/watt:explore, and/watt:help— via the Interactive-input choices that close the run (and/watt:helpearlier, when a check stays stuck and they want a human).
The flow
One beat per turn. Throughout, keep a setup checklist on screen and mark each item with a ✓ the moment it clears — so the user always sees where they are and what's left:
- Account type
- Supported platform
- Signal Graph connected
- File downloads on
- Automatic updates on
Show the checklist however reads clearest on this surface — the model and host decide the shape. Decisions, though, are Interactive inputs — Claude's native clickable options — robust even when a render surface is part of what's misconfigured, and a typed reply always wins.
One path, not all of them. Steps 5–7 each have a personal-account path and an organization-account path. Step 2 settles which one is theirs — so from there on, show only that path. Never paste both branches, every doc link, and every what-if into the chat; that's noise. Give the user the one move that's theirs right now, plus a single link to the guide if they want to follow along — and let the tappable choices funnel them.
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.
- yesterday First seen · 140 lines · 119 tokens per session scan A 1e2c458c5fc1
configure is a skill published in the GitHub repository wattdata/plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 119 tokens to every session and 4,277 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…