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 san-npm/skills-ws --skill sales-funnelgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/sales-funnel)<a href="https://agentmods.dev/skills/san-npm/skills-ws/sales-funnel"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/sales-funnel/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/san-npm/skills-ws/sales-funnel"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/sales-funnel.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 | $0.00085 | $0.07781 |
| Opus 5.5 | $0.00034 | $0.03112 |
| Sonnet 5.5 | $0.00017 | $0.01556 |
| Haiku 4.5 | $0.00009 | $0.00778 |
Grade A, and why
sales-funnel 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sales Funnel
Design conversion paths, instrument them, find the leak, and ship experiments. This skill assumes you have (or will gather) five inputs: product/offer, ICP, ACV / price point, sales motion (PLG self-serve, sales-led, hybrid, transactional ecommerce), and current funnel analytics. Sales motion drives nearly every decision below — a $30/mo PLG tool and a $120k/yr enterprise contract share almost no funnel mechanics.
Related skills: use lead-scoring for the qualification/routing logic that sits between MOFU and BOFU; use social-media-kit for the TOFU content production this funnel consumes.
0. Diagnostic workflow (run this first)
Do not propose tactics before you've measured. Work the funnel in this order.
- Gather inputs. Product, ICP (firmographic + role + pain), ACV, sales motion, sales cycle length, and current analytics (stage-by-stage volumes + conversion rates for the last 1–3 months).
- Map the literal stages the buyer actually moves through (not the textbook ones). For PLG: Visitor → Signup → Activated → Paid → Expanded. For sales-led: Visitor → MQL → SQL → Opportunity → Closed-Won. Name each stage by an observable event, not a feeling.
- Compute step conversion rates and absolute drop-off counts at every transition. Rank leaks by recovered revenue = (stage entrants) × (lift you believe is achievable) × (downstream conversion to revenue) × (ACV). The biggest %-drop is rarely the biggest $ opportunity.
- Diagnose the top leak. Is it traffic quality (wrong ICP in), messaging (right people bounce), friction (they try and fail), trust (they stall at decision), or follow-up (no nurture)? Each has different fixes.
- Form a hypothesis in the form: "For [segment] at [stage], [change] will lift [step metric] from X% to Y% because [mechanism]." Tie to a guardrail metric so you don't win the step but lose revenue.
- Design the experiment (see §8). Pick A/B vs. before-after vs. holdout based on traffic. Pre-register the primary metric and minimum detectable effect.
- Define the events you must fire to even measure this (see §6). If you can't measure the step, instrument before you optimize.
- Set guardrails (see §9) — disclosure, consent, claims substantiation — before shipping, especially for scarcity/urgency, pricing, and email.
- Produce implementation tasks: copy/design changes, event tracking, CRM stage definitions, lifecycle automations, and the analysis query.
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.
- 2mo ago First seen · 370 lines · 85 tokens per session scan A 8fe1b8b2a37a
sales-funnel is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 7,781 once invoked, about $0.0003 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 2026-09-07.
sales-funnel compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sales-funnelsan-npm/skills-ws | Skill | 4 | 1mo ago | MIT | A | 85 | 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 |