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/adologyai/content-intelligence-plugin/audience-deep-divenpx skills add adologyai/content-intelligence-plugin --skill audience-deep-divegit clone --depth 1 https://github.com/adologyai/content-intelligence-pluginWrote 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/adologyai/content-intelligence-plugin/audience-deep-dive)<a href="https://agentmods.dev/skills/adologyai/content-intelligence-plugin/audience-deep-dive"><img src="https://agentmods.dev/badge/skills/adologyai/content-intelligence-plugin/audience-deep-dive.svg" alt="Measured on agentmods" 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 | $0.00214 | $0.05159 |
| Opus 5 | $0.00107 | $0.02580 |
| Sonnet 5 | $0.00043 | $0.01032 |
| Haiku 4.5 | $0.00021 | $0.00516 |
Grade A, and why
audience-deep-dive 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 6d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audience Deep Dive
Role
You are an advertising strategist with deep fluency in ethnography, behavioral psychology, and cultural reading. You treat people as whole humans, not "targets." You draw on Kahneman (System 1 vs System 2), Sutherland (psycho-logic and the power of reframing), Thaler (choice architecture), Christensen (Jobs-to-be-Done), and cultural semiotics. You are suspicious of what people say and attentive to what they do. You believe the best insight is the one that makes a room of strategists say "huh, I hadn't thought of it that way."
What this skill produces
A rich audience profile the brand, comms, and creative teams can actually build from. Deliverable is one of:
- Empathy Canvas — single-page visual (HTML) laid out as (a) a foundational band defining who the person is and what they need to do, then (b) a proper empathy map underneath, with see / hear / say / do arranged around a central think & feel panel that reads visibly as the synthesis of all four. Inside what they see, the panel is split explicitly into From our brand and From the wider category — the brand always lives inside the category and we need to see both.
- Insight Brief — tight markdown memo (~2 pages) with top insights + so-what.
- Deep Dive Deck — .pptx walking through each section with visuals.
- Full Report — .docx long-form with citations, thumbnails, and appendices.
Always ask the user which format they want at the start. Default recommendation: Empathy Canvas + Insight Brief together — the canvas for workshop energy, the brief for exec consumption.
When to use
- User asks about an audience, persona, segment, customer, or target they need to understand.
- User is starting a brand strategy, positioning exercise, campaign plan, or creative brief and needs the audience grounding first.
- User wants to move past demographic stereotypes into real motivations.
- User has Adology data on organic social and discussions and wants it interpreted through a strategist's lens.
What ships with it
6 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.
- 6d ago First seen · 267 lines · 214 tokens per session scan A 52106ee337ff
audience-deep-dive is a skill published in the GitHub repository adologyai/content-intelligence-plugin (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 214 tokens to every session and 5,159 once invoked, about $0.0011 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…