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-analyze-searchnpx skills add wattdata/plugin --skill audience-analyze-searchgit 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 | $0.00105 | $0.02085 |
| Opus 5 | $0.00053 | $0.01043 |
| Sonnet 5 | $0.00021 | $0.00417 |
| Haiku 4.5 | $0.00011 | $0.00209 |
Grade A, and why
audience-analyze-search 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 2d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze a market from a brief
Purpose
audience-analyze-search is the way into the read for a user who arrives with a brief, not signals — "who's in the market for roofing near Nashville", "profile this audience". It discovers the signals behind the brief, organizes them into three pools, lets the operator steer which signals land in which pool, materializes the audience, and hands it to the shared read. Size is an output, never a target — there's no band and no strategy procedure; the headcount is whatever the composed signals land at.
This is a delta over audience-analyze: the unique work here is getting from a brief to a built signal stack; once that stack exists, the read and the shareable report are the parent's shared procedure (audience-analyze → The read & report), composed with verbatim — not restated.
Works with
- Called by: the
audience-analyzerouter, when the user brought a brief and no signals. - Runs inline (the same discovery and scoring explore uses, here feeding a built-and-read audience):
- signal discovery — one concept per beat: a pool's concept (in the user's phrasing, tagged with its role) → validated candidate signals with evidence (
context/discovery.md). - signal scoring — the gathered signals scored against the model (relevance · freshness · rarity/specificity · breadth/size · coverage), grounded on the brief, so the operator can see how each stacks up and curate — traits-only, never a set of people (
context/scoring.md). - adjacencies (optional, at a pivot checkpoint) — adjacent concepts / unprobed domains worth adding to a pool (
context/adjacencies.md).
- signal discovery — one concept per beat: a pool's concept (in the user's phrasing, tagged with its role) → validated candidate signals with evidence (
- Runs the read inline — the profiling procedure (
context/profiling.md) in mode A (the built stack) → the two-section read; the parent's shared read, run inline on the main thread.
Language
Inherits the parent's table (signals / must-haves / exclusions; lift explained once; sample named). Internally the three pools map to the boolean shape — defining → OR (core), must-have → AND (must_have), exclusion → AND_NOT (exclusion) — but the operator only ever sees defining signals, must-haves, exclusions. No AND/OR/NOT, no boolean-"pools" jargon at the surface (signal pool, the kept-signals carrier, is the user's word and fine).
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.
- 2d ago First seen · 81 lines · 105 tokens per session scan A 3120c3cad03f
audience-analyze-search is a skill published in the GitHub repository wattdata/plugin (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 2,085 once invoked, about $0.0005 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
benchmark-methodology
Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence, enterprise-readiness, thought leadership, pricing, client's strategic tension) with explicit 1–5 rubrics and a tension-plot.…
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
write-like-meng-on-x
Write, rewrite, review, or continuously refine X/Twitter posts in Meng To's current voice using his deduplicated authored-post corpus, personal and product context, shared resources, and Content repo evidence. Use when asked to improve a tweet in Meng's tone, draft an original post, reply, thread, resource share, or…
youtube-thumbnail
Generate a branded YouTube thumbnail from a video title. Uses a reference photo of the creator, high-CTR thumbnail principles, and brand colours to produce a ready-to-generate image prompt for Gemini. Use this skill whenever the user says "thumbnail", "youtube thumbnail", "build me a thumbnail", or wants a video cover…
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…