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/audience-analyzenpx skills add wattdata/plugin --skill audience-analyzegit 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 | $0.00145 | $0.03807 |
| Opus 5 | $0.00072 | $0.01903 |
| Sonnet 5 | $0.00029 | $0.00761 |
| Haiku 4.5 | $0.00015 | $0.00381 |
Grade A, and why
audience-analyze 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 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.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze an audience
Purpose
audience-analyze — the read step behind /watt:audience — answers the question generate can't: generate guaranteed an audience's size (or, for a profile, measured its headcount); this read shows what it means. The user walks away with a dashboard in two halves: your signals — the stack's own signals by share and how many each person hits — and discovered — the net-new traits that define these people against the world by lift, plus segmentation, skews, freshness. For a market profile, this read is the deliverable: on request it writes the two halves to a self-contained shareable report file.
There are three ways into that read, by what the user brings — and this skill routes to the one that fits:
- a brief — they describe the audience in business terms and want the signals discovered for them →
audience-analyze-search. - signals they already hold — a signal stack from generate, an explore pool, or a list of signals they name →
audience-analyze-signal. - a list of people — identifiers to resolve and profile →
audience-analyze-list(discovered half only — no signals were specified).
Route; don't run. Your job at this level is the routing question and the shared canon below — the language, the aggregates-only lane, and the read-and-report procedure every leaf composes with. The leaf does the discovery, the inline profiling run, and the render.
Works with
- Called by: the
/watt:audiencerouter, or a sibling leaf's offer (audience-generateat its landing — a build to sanity-check, or a profile whose report is the deliverable;audience-activateafter delivery) — with a built audience in session, a re-supplied audience record, or a fresh read-shaped ask. - Hands off to: the three leaves —
audience-analyze-search— brief → discover signals → organize into pools → operator pivot → materialize → read.audience-analyze-signal— a supplied stack/signal list → materialize → read (skips discovery).audience-analyze-list— a supplied list of people, as identifiers (resolve to entities) or as already-resolved entity IDs (a roster from grouping — skip the resolve) → discovered-only read.
What ships with it
1 file 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.
- yesterday First seen · 128 lines · 145 tokens per session scan A 622d44771d92
audience-analyze is a skill published in the GitHub repository wattdata/plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 145 tokens to every session and 3,807 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
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…