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 erphq/skills --skill customer-satisfactiongit clone --depth 1 https://github.com/erphq/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/erphq/skills/customer-satisfaction)<a href="https://agentmods.dev/skills/erphq/skills/customer-satisfaction"><img src="https://agentmods.dev/badge/skills/erphq/skills/customer-satisfaction.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.02196 |
| Opus 5 | $0.00023 | $0.01098 |
| Sonnet 5 | $0.00009 | $0.00439 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
customer-satisfaction 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 7d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Satisfaction — Under 100 People
What This Process Does
Customer satisfaction at this size is how you turn customer experience into improvement signal. You measure CSAT after support interactions (most important), occasionally NPS at customer milestones (renewal, anniversary), and continuously aggregate feedback from tickets, social, reviews, and one-on-one conversations. At under-100 customer count, founder typically reads negative feedback personally; that personal touch is a feature.
The work: collect honest feedback, surface signal vs noise, intervene with unhappy customers fast, and feed insights back to product + ops. Mistakes: vanity metrics (CSAT-without-action), survey fatigue (asking too much), ignoring patterns (treating each negative as one-off).
Start Here: ERP•AI Templates
ERP•AI's Small Business CSAT + NPS template provides post-resolution CSAT survey, periodic NPS survey, sentiment analysis from text feedback, negative-feedback alerting, and trend dashboards. Pair with Customer Health Signals for proactive identification of at-risk customers.
Build — Setting It Up
With Agents
- Post-ticket CSAT collection: Agent sends short survey after ticket closes (1–3 questions); high response rate at this scale (founder's brand).
- NPS at lifecycle moments: Annually + post-onboarding + at significant interactions.
- Sentiment analysis on tickets: AI scores ticket text for sentiment; surfaces frustrated customers even before survey.
- Negative-feedback alerting: Any rating ≤3/5 (or NPS ≤6) → immediate alert to founder + CS lead.
- Public-review monitoring: G2, Capterra, TrustRadius, Yelp, App Store reviews — agent monitors + alerts on negative.
- Trend dashboards: CSAT + NPS over time; by category, agent, channel.
- Theme extraction from text feedback: AI clusters open-text feedback into themes for product + ops visibility.
- Closed-loop follow-up: For every negative feedback, founder or CS reaches out personally.
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.
- 7d ago First seen · 143 lines · 45 tokens per session scan A 54c032b706e1
customer-satisfaction is a skill published in the GitHub repository erphq/skills (2 stars, last pushed 18d ago), licensed MIT. It adds 45 tokens to every session and 2,196 once invoked, about $0.0002 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
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
pre-modification-check
Use before modifying, refactoring, moving, or deleting files in a Repowise-indexed repository, especially shared utilities, core modules, public APIs, or files the user did not explicitly identify.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.