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 Gingiris-1031/gingiris-skills --skill hardware-saas-gtmgit clone --depth 1 https://github.com/Gingiris-1031/gingiris-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/gingiris-1031/gingiris-skills/hardware-saas-gtm)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/hardware-saas-gtm"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/hardware-saas-gtm/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/gingiris-1031/gingiris-skills/hardware-saas-gtm"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/hardware-saas-gtm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 230 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00582 | $0.04246 |
| Opus 5 | $0.00291 | $0.02123 |
| Sonnet 5 | $0.00116 | $0.00849 |
| Haiku 4.5 | $0.00058 | $0.00425 |
Grade A, and why
hardware-saas-gtm 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 11d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hardware + SaaS GTM Playbook / 硬件+软件订阅一体 GTM 实操手册
Built from verified case data: Plaud (KS $1.1M, $100M ARR), Insta360 (70%+ overseas revenue, 2025 STAR Market IPO), DJI (70–80% global drone market share) 数据来源说明: 所有关键数字均标注可信度（⭐⭐⭐高 / ⭐⭐中 / ⭐低）；完整核验表见
references/case-studies.md
When to Use This Skill / 什么时候用这个 Skill
Use this skill when you are:
- Planning a Kickstarter / Indiegogo / Makuake campaign for a hardware product
- Designing a hardware + software subscription bundle (device as entry, SaaS as margin)
- Building a KOL outreach strategy for a physical product
- Validating PMF for a consumer hardware product pre-launch or post-shipping
- Deciding when and how to localize into Japan, Europe, or other non-English markets
- Designing a UGC/community flywheel around a physical device
不适合此 Skill 的场景 (Out of scope):
- Pure SaaS products without a physical component → use
gingiris-b2b-growthorgingiris-launch - Open source software GTM → use
gingiris-opensource - App store growth → use
gingiris-aso-growth
Core Mental Model: Device as Funnel / 核心模型：设备即漏斗
Hardware + SaaS is not two businesses. It is one funnel:
Device Purchase (one-time)
→ Free Tier Activation (habit formation, 30–90 days)
→ Friction Point (usage limit, feature gate)
→ Paid Subscription (PMF arena, where retention is measured)
→ Enterprise / Team Upsell (ARPU expansion)
The device is not the product. The device is the ticket. The physical device:
- Pre-qualifies intent: someone who paid $89–$159 for hardware has demonstrated spending commitment far beyond a free trial signup
- Creates sunk-cost lock-in: "I already bought it" psychology drives subscription conversion
- Generates content: unboxing, demo, reveal moments are free advertising inventory
Plaud benchmark ⭐⭐⭐: KS early-bird $89 device + first-year subscription $39 = $128 total — cheaper than the $159 MSRP device alone. Early backers entered the subscription ecosystem before consciously evaluating it.
What ships with it
3 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.
- 11d ago First seen · 231 lines · 582 tokens per session scan A 12bb8d87ea1d
hardware-saas-gtm is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (79 stars, last pushed 6d ago), licensed MIT. It adds 582 tokens to every session and 4,246 once invoked, about $0.0029 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 2026-08-30.
Other skills, from other repositories
dhx-components-sourcing
Real-time global electronic components sourcing, BOM matching, cross-referencing, and China PCBA factory sourcing agent powered by DHX Tech.
dhx-components-sourcing
Real-time global electronic components sourcing, BOM matching, cross-referencing, and China PCBA factory sourcing agent powered by DHX Tech.
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
p1-spec-research-policy
Internal reference: p1 spec research policy (agent-loaded; do not invoke).
rtl-p3-uarch-policy
Internal reference: rtl p3 uarch policy (agent-loaded; do not invoke).
codec-conformance-eval
Evaluate C ref-model decoder against JVET/JCTVC conformance bitstreams (bitexact/MD5) — 'decoder conformance'; C-level, not RTL (rtl-conformance-test).