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 customer-feedbackgit 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/customer-feedback)<a href="https://agentmods.dev/skills/san-npm/skills-ws/customer-feedback"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/customer-feedback/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/customer-feedback"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/customer-feedback.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 | $0.00074 | $0.07409 |
| Opus 5 | $0.00037 | $0.03705 |
| Sonnet 5 | $0.00015 | $0.01482 |
| Haiku 4.5 | $0.00007 | $0.00741 |
Grade A, and why
customer-feedback 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 10d 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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Feedback
Metric Framework
| Metric | Question | Scale | When to Use |
|---|---|---|---|
| NPS | "How likely are you to recommend [product] to a friend or colleague?" | 0-10 (Detractor 0-6, Passive 7-8, Promoter 9-10). NPS = %Promoters − %Detractors, range −100..+100 | Relationship health, quarterly+ |
| CSAT | "How satisfied were you with [interaction]?" | 1-5 (1 Very dissatisfied → 5 Very satisfied). CSAT% = (count of 4+5) / total responses × 100 | Post-transaction, support close |
| CES | "[Product] made it easy for me to [handle my issue]." | Agreement scale. Normalize to %top-2-box | Post-task completion |
| PMF Score | "How would you feel if you could no longer use [product]?" | Very / Somewhat / Not disappointed (Sean Ellis test; target >40% "very") | Product-market fit |
Scale wording matters — pick a standard and stick to it
The single biggest source of "our scores don't match the benchmark" is silently changing scale length, labels, or polarity. Lock these down before launch and never change them mid-program (a change resets your trend line).
- NPS — always 0-10, 11 points, label only the endpoints ("Not at all likely" / "Extremely likely"). Report the net score AND the raw distribution (a +30 from 60/30/10 behaves nothing like a +30 from 30/70/0).
- CES — two competing conventions exist; choose one and document it:
- CES 2.0 (recommended) — agreement statement "[Product] made it easy to handle my issue" on a 7-point scale (1 Strongly disagree → 7 Strongly agree). Score = mean, or %top-2-box (6-7). This is the modern CEB/Gartner form; higher = less effort = better.
- Legacy CES 1.0 — effort question "How much effort did you personally have to put forth?" on 1-5 or 1-7 where higher = MORE effort = worse. Polarity is inverted vs. CES 2.0 — mixing the two silently flips your trend. Avoid unless you have historical data on it.
- 5-point agreement is acceptable for low-literacy/mobile audiences; just don't compare a 5-point mean to a 7-point mean. Always normalize cross-survey comparisons to %top-2-box rather than raw means.
- CSAT — 1-5 is standard; some teams use 1-3 (mobile) or 1-7. Report %satisfied (top-2-box) for comparability, not the mean (means hide bimodal "love it / hate it" splits).
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.
- 10d ago First seen · 454 lines · 74 tokens per session scan A 83f6d76258b9
customer-feedback is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 7,409 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…