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 swan-gtm/gtm-skills --skill handle-demo-requestgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/handle-demo-request)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/handle-demo-request"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/handle-demo-request/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/swan-gtm/gtm-skills/handle-demo-request"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/handle-demo-request.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 Excessive Agency · line 54 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00142 | $0.02759 |
| Opus 5 | $0.00071 | $0.01380 |
| Sonnet 5 | $0.00028 | $0.00552 |
| Haiku 4.5 | $0.00014 | $0.00276 |
Grade A, and why
handle-demo-request 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handle a demo request
Runs on every inbound demo request. Produces a CRM record, a fit-and-persona verdict, exactly one outbound email (or none), and a single alert to the team — with the request routed by whether the company is a fit and whether the person is a buyer, never by a tier number alone.
The default handling — route every demo request to a rep and book the meeting — is wrong in both directions. It sends your team into meetings with companies that were never going to buy, and it treats a junior analyst at a perfect-fit account as if they were the CRO.
Template placeholders
Replace every {{...}} before enabling. Full setup list in references/setup-customization-checklist.md.
{{CRM}}— where contacts and companies live (e.g. HubSpot, Salesforce, Attio).{{ALERT_CHANNEL}}— the single channel every demo request posts to, whatever the outcome.{{MQL_CHANNEL}}— where qualified leads surface. Owned by your scoring pass, never posted to from here.{{SALES_SENDER}}— the person booking emails come from.{{BOOKING_LINK}}— their calendar link.{{TRIAL_LINK}}— your self-serve entry point.{{SELF_SERVE_FLOOR}}— the company size below which an account is self-serve, not sales-assisted (default: under 50 employees).{{FUNDED_OVERRIDE}}— the funding-and-size combination that pulls an account back onto the sales-assisted path regardless (default: more than 30 employees and more than $10M raised).{{TOP_TIERS}}— the tiers that justify an MQL stage rather than an awareness stage.{{DECISION_MAKER_TITLES}}— the titles that count as buying authority in your market.
Step 1 — Gate the email before spending anything
Extract the work email. Stop when there is no email, or when it is a consumer domain — gmail, outlook, hotmail, yahoo, icloud, proton, and the rest.
Post a low-priority note to {{ALERT_CHANNEL}} saying a demo request arrived that could not be processed, include the raw address if there was one, and end. Do not enrich, do not write to {{CRM}}, do not send anything.
What ships with it
2 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.
- 9d ago First seen · 137 lines · 142 tokens per session scan A 130dcb155379
handle-demo-request is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 142 tokens to every session and 2,759 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
proposals
Use when writing the document a buyer reads to say yes — a commercial proposal or Statement of Work, turning discovery notes into a scoped and priced document, adding tiers so the middle one wins, or diagnosing a proposal that will not close. NOT the binding legal agreement with its liability and IP clauses (that is…
co-founder-dynamics
Complete co-founder playbook for technical founders — finding co-founders, equity splits (dynamic and static), co-founder agreements, vesting schedules, working relationships, conflict resolution, co-founder breakups, and the "dating before marrying" framework. Use when looking for a co-founder, structuring a founding…
support-tool-stack
Customer support platform selection, setup, and optimization — Intercom, Zendesk, Front, Help Scout, HubSpot Service Hub, Linear, and AI-native tools. Use when choosing a support platform, migrating tools, setting up help desk workflows, designing ticket routing, building macros and saved replies, or integrating…
advisor-recruitment
Strategic advisor recruitment for B2B SaaS founders. Use when building advisory board, recruiting individual advisors, structuring advisor compensation (equity grants), defining advisory scope, leveraging advisors for intros/references/customers, and managing ongoing advisor relationships.
engineer-to-founder
Translate engineering strengths into founder-led GTM: customer discovery, positioning, demos, technical proof, founder sales habits, and first repeatable motion. Use when a technical founder needs to sell, do customer interviews, explain value without feature dumping, or build GTM confidence.