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 varunk130/ai-gtm-skill-library --skill voice-of-customergit clone --depth 1 https://github.com/varunk130/ai-gtm-skill-libraryWrote 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/varunk130/ai-gtm-skill-library/voice-of-customer)<a href="https://agentmods.dev/skills/varunk130/ai-gtm-skill-library/voice-of-customer"><img src="https://agentmods.dev/badge/skills/varunk130/ai-gtm-skill-library/voice-of-customer/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/varunk130/ai-gtm-skill-library/voice-of-customer"><img src="https://agentmods.dev/badge/skills/varunk130/ai-gtm-skill-library/voice-of-customer.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 | $0.00073 | $0.01402 |
| Opus 5 | $0.00036 | $0.00701 |
| Sonnet 5 | $0.00015 | $0.00280 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
voice-of-customer 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice of Customer (ECHO Framework)
Design a Voice-of-Customer program that turns raw feedback into routed, prioritized, evidence-backed actions - not a quarterly NPS report nobody reads. ECHO replaces ad-hoc surveys with a multi-source signal pipeline that PMs, CS, and marketing all rely on.
Core Principle
VoC fails when it conflates collection with insight. A survey isn't a program. ECHO standardizes how signal is elicited, themed, prioritized, and closed - with the loop back to the customer being the most often skipped step.
The ECHO Framework
| Letter | Stage | The Question |
|---|---|---|
| E | Elicit | What sources are tapped, with what cadence, and how is bias controlled? |
| C | Categorize | How is feedback themed, tagged, and made queryable? |
| H | Highlight | What prioritization frame separates signal from noise? |
| O | Operationalize | Who owns the action, what's the SLA, and how is the loop closed with the customer? |
Elicitation Sources
A robust program reads from multiple channels and triangulates:
| Source | Quality | Volume | Bias Risk |
|---|---|---|---|
| Surveys (NPS, CSAT, CES) | Quantitative + open-ended | High | Survey fatigue, selection bias |
| Win / loss interviews | Deep qualitative | Low | Selection bias toward closed deals |
| Customer advisory board | Strategic qualitative | Very low | Top-customer bias |
| Support tickets | Reactive, problem-focused | Very high | Skewed to broken, not desired |
| Product analytics | Behavioral, not stated | Very high | Observation without intent |
| CSM call notes | Contextual qualitative | High | CSM filter |
| Sales call recordings | Pre-sale voice | High | Sales-stage filter |
| Community / public reviews | Honest, public | Medium | Vocal-minority bias |
| Churn / contraction interviews | High-signal | Low | Painful but most actionable |
Theming & Tagging
Without disciplined theming, VoC becomes a junk drawer. Adopt:
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.
- 12d ago First seen · 115 lines · 73 tokens per session scan A 37a1d67e8d89
voice-of-customer is a skill published in the GitHub repository varunk130/ai-gtm-skill-library (6 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,402 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 2026-08-31.
Other skills, from other repositories
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
110-java-maven-best-practices
Use when you need to review, improve, or troubleshoot a Maven pom.xml file — including dependency management with BOMs, plugin configuration, version centralization, multi-module project structure, build profiles, or any situation where you want to align your Maven setup with industry best practices. This should…