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/agent-engineer-master/skill-engineer/marketing-plannpx skills add Agent-Engineer-Master/skill-engineer --skill marketing-plangit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/marketing-plan)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/marketing-plan"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/marketing-plan.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 | $0.00170 | $0.03235 |
| Opus 5 | $0.00085 | $0.01618 |
| Sonnet 5 | $0.00034 | $0.00647 |
| Haiku 4.5 | $0.00017 | $0.00324 |
Grade C, and why
marketing-plan scanned grade C 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer --> How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Plan
Produces a full go-to-market marketing plan for a new online business.
Process
Phase 1: Context Intake
Before asking questions, check if a shared context file exists (e.g. product-marketing-context.md, _store-state.md, or similar product brief in the working directory). If found, read it and pre-fill answers. Only ask questions whose answers are not already available.
Ask these 7 questions (all required before proceeding):
- Product/service — What are you selling and how is it delivered? (1-2 sentences)
- Business model — SaaS / DTC ecommerce / service / marketplace / other?
- Stage — Pre-launch (no customers), early (1-50 customers), or growing (50+)?
- Geography — Primary target market (country/region)?
- Budget — Bootstrapped (no ads), low (<$1k/mo), medium ($1k-$10k/mo), or well-funded?
- Key constraint or unfair advantage — One thing that limits or enables this launch.
- Existing audience — Do you have a personal brand, newsletter, social following, or community presence? If yes: where and approximate size.
Store answers as a context card. Load references/business-type-guide.md to apply business-type rules. If Q7 reveals an existing audience, check the Personal Brand Flywheel section of that file and apply the modifier before generating channel options.
Phase 2: Beachhead Market + ICP
Principle: The most common GTM failure is targeting everyone. Define the smallest winnable segment first.
Using context card and references/frameworks.md (JTBD + beachhead sections):
- Size the market: TAM -> SAM -> beachhead
- Generate 3 ICP options as JTBD statements: "When [trigger], [persona] wants to [outcome], so they can [deeper goal]."
- For each option, rate: market size (S/M/L), competition (low/med/high), reachability (hard/med/easy)
GATE A — present 3 ICP options. Wait for user to choose one. If none fit, ask which element to change (trigger, persona, or outcome) and generate 3 new options.
What ships with it
10 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.
- assets/approved-examples/.gitkeep 0 B
- assets/plan-template.md 12 KB
- evals/evals.json 7.5 KB
- evals/judge.md 3.1 KB
- evals/rubric.md 8.3 KB
- references/business-type-guide.md 14 KB
- references/edge-cases.md 193 B
- references/execution-playbooks.md 12 KB
- references/frameworks.md 10 KB
- references/learnings.md 554 B
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.
- 5d ago First seen · 241 lines · 0 tokens per session scan C 1d90efd4c4dc
marketing-plan is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 170 tokens to every session and 3,235 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
gsd-ns-manage
Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.