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 atypica-ai/marketing-skills --skill plan-as-consultantgit clone --depth 1 https://github.com/atypica-ai/marketing-skillsWrote 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/atypica-ai/marketing-skills/plan-as-consultant)<a href="https://agentmods.dev/skills/atypica-ai/marketing-skills/plan-as-consultant"><img src="https://agentmods.dev/badge/skills/atypica-ai/marketing-skills/plan-as-consultant/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/atypica-ai/marketing-skills/plan-as-consultant"><img src="https://agentmods.dev/badge/skills/atypica-ai/marketing-skills/plan-as-consultant.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 | $0.00132 | $0.01889 |
| Opus 5.5 | $0.00053 | $0.00756 |
| Sonnet 5.5 | $0.00026 | $0.00378 |
| Haiku 4.5 | $0.00013 | $0.00189 |
Grade A, and why
plan-as-consultant 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 2mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan as Consultant
This skill is adapted from atypica.AI — a business research platform that uses AI agents to conduct qualitative consumer studies. The research planning methodology here comes directly from atypica's production consulting workflow.
When someone comes to you with a business question, your job is to help them think like a consultant before they start researching. The goal is a research plan: a clear plan that tells them what to investigate, how to investigate it, and what a useful final output looks like.
A good research plan prevents wasted effort. Without one, people dive into gathering information without knowing what they're looking for or how they'll use it.
Your role
Approach this as a professional business consultant who has worked at consulting firms and taught MBA courses. You're deeply familiar with how to categorize business problems and which analytical frameworks work best for each type.
Your job is not to answer the research question — the research hasn't happened yet. Your job is to plan how to answer it well.
How to produce a research plan
Work through these five steps in order. Adapt the depth to how clearly the person has articulated their question.
Step 1: Understand the problem
Before anything else, get clear on what's actually being asked.
- Who is asking? Visualize the person behind this question — are they a product manager trying to prioritize features, a founder deciding which market to enter, a marketer designing a campaign? Their role shapes what kind of output they need.
- What category of problem is this? Business problems tend to fall into recognizable types: market segmentation, product positioning, pricing, feature prioritization, competitive strategy, user behavior understanding, brand perception, channel selection. Name the category.
- What industry/context? The same question ("which features matter most?") looks different for a B2B SaaS product vs. a consumer skincare brand.
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.
- 2mo ago First seen · 159 lines · 132 tokens per session scan A e52919ab1742
plan-as-consultant is a skill published in the GitHub repository atypica-ai/marketing-skills (45 stars, last pushed 7mo ago), licensed MIT. It adds 132 tokens to every session and 1,889 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
plan-as-consultant compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plan-as-consultantatypica-ai/marketing-skills | Skill | 45 | 7mo ago | MIT | A | 132 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |