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 LeadMagic/gtm-skills --skill support-tool-stackgit clone --depth 1 https://github.com/LeadMagic/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/leadmagic/gtm-skills/support-tool-stack)<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/support-tool-stack"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/support-tool-stack/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/leadmagic/gtm-skills/support-tool-stack"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/support-tool-stack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.03651 |
| Opus 5 | $0.00043 | $0.01826 |
| Sonnet 5 | $0.00017 | $0.00730 |
| Haiku 4.5 | $0.00009 | $0.00365 |
Grade A, and why
support-tool-stack 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 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.
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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support Tool Stack
Overview
Your support stack determines whether customers feel heard or abandoned. The mistake: picking the tool your last company used instead of the tool that matches your current stage, team size, and support philosophy. A 3-person startup on Zendesk Enterprise ($150/agent/mo) is burning money. A 50-person team on a shared Gmail inbox is losing customers to slow responses. This skill covers platform selection, setup, and optimization across every stage and support philosophy.
Authoritative Foundations
- Intercom — Conversational Support Framework — Conversational Support Framework
- Plain — API-first headless support and BYOAI via MCP — Model Context Protocol — tool servers for agent-safe CRM and enrichment access.
- Zendesk — Omnichannel CX Maturity Model — Omnichannel CX Maturity Model
- Help Scout — Support-Driven Growth (Bezos: customer obsession) — Support-Driven Growth (Bezos: customer obsession)
- Klaus/Maestro QA — Support Quality Framework — Support Quality Framework
When to Use
Trigger phrases: "choose support platform", "Intercom vs Zendesk", "help desk setup", "support tool stack", "migrate support platform", "set up ticketing", "customer support software", "Front vs Help Scout", "AI support tools", "help desk comparison", "Plain vs Intercom", "BYOAI support", "headless support stack"
Headless / BYOAI path
API-first stack (often with Attio CRM): Plain for support infrastructure —
GraphQL API, embedded headless portal, Slack/email channels, native MCP for
Jesse/Claude agents. BYOAI instead of vendor AI (Fin). Full pattern:
skills/customer-success/headless-support/references/byoai-headless-stack.md. MCP config: mcp-setup.
Choose Intercom when you need Messenger + Fin without engineering a custom portal.
Platform Selection by Stage
Stage 0: Pre-Launch / $0-500K ARR (Founder Doing Support)
You need: Shared inbox. Basic knowledge base. Minimal cost.
| Tool | Pricing | Best For |
|---|---|---|
| Front | $19-59/seat/mo | Shared inbox with internal comments, assignment |
| Help Scout | $20-65/seat/mo | Docs-first support, clean UX, Beacon widget |
| Linear | $8-14/seat/mo | If support = bug reports / feature requests |
| Plain | Custom / startup program | API-first product, embed support in-app, BYOAI via MCP |
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.
- 5d ago First seen · 365 lines · 86 tokens per session scan A 9d4a2061ccbe
support-tool-stack is a skill published in the GitHub repository LeadMagic/gtm-skills (48 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 3,651 once invoked, about $0.0004 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
onboarding-handoff
Run the Won→onboarding handoff — the seam most teams drop. Trigger when a deal is marked won/closed-won, when the user says "we won X", "hand this off to onboarding", "kick off the new customer", or "onboarding checklist".
product-signal
Route post-sale and field signals into product's roadmap queue, and write the buyer-facing line for anything shipped. Trigger when the user says "what should product hear", "triage the roadmap signals", "route this to product", "feature request", or "what does this feature mean for the buyer".
client-health-review
Sweep every client folder and report what needs attention — renewals inside 90 days, accounts in their first 90 days, missing success definitions, accounts with no QBR in two quarters, unfilled proof stubs, stale reviews, and referral-ready accounts. Use for portfolio review, retention review, or before starting new…
client-onboarding
Turn a won deal into a first-90-days plan with a written success definition, named stakeholders and what each judges success by, and checkpoints at day 14, 30, and 90. Use right after a win, when a new client starts, or when an existing account has no agreed definition of what success means.
session-relay
Maintain lightweight project continuity for long GTM Brain builds by keeping a relay README as the source of truth, archiving transcript links without reading them by default, and producing concise handoff prompts.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…