gph-mcp-server: Skill for Claude Code

.claude/skills/customer-voice/SKILL.md

customer-voice is a skill for Claude Code from Crindo2/gph-mcp-server. It costs 62 tokens per session (1,303 once invoked), scanned A, original, MIT.

A writing guide for customer-facing text, such as product pages, forms, emails, offers, error messages and assistant messages. It asks writers to sound like a knowledgeable person speaking directly to one reader.

In plain words
What is it for?
Use it to write or review copy shown to customers, including interface text, marketing messages, status updates and help content.
Why use it?
It removes stiff, generic wording and helps readers understand the message and its reasoning. It also encourages using the reader's actual facts instead of vague labels.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is Crindo2/gph-mcp-server's own configuration. It tells Claude Code how to work on gph-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gph-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Crindo2/gph-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Crindo2/gph-mcp-server/main/.claude/skills/customer-voice/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Crindo2/gph-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for customer-voice

README.md
[![agentmods](https://agentmods.dev/badge/skills/crindo2/gph-mcp-server/customer-voice/github.svg)](https://agentmods.dev/skills/crindo2/gph-mcp-server/customer-voice)
Your own site
<a href="https://agentmods.dev/skills/crindo2/gph-mcp-server/customer-voice"><img src="https://agentmods.dev/badge/skills/crindo2/gph-mcp-server/customer-voice/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.

agentmods 80×15 button for customer-voice

Your own site · 80×15
<a href="https://agentmods.dev/skills/crindo2/gph-mcp-server/customer-voice"><img src="https://agentmods.dev/badge/skills/crindo2/gph-mcp-server/customer-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00062 $0.01303
Opus 5.5 $0.00025 $0.00521
Sonnet 5.5 $0.00012 $0.00261
Haiku 4.5 $0.00006 $0.00130

Measured 3d ago against content hash d3d1eddf7b75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

customer-voice 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 3d 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.

.claude/skills/customer-voice/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Customer voice

Anything a customer reads should sound like a knowledgeable person explaining it to them across a desk. Readers spot machine-written text in a sentence or two, and once they do they trust the content less. Natural text is also simply easier to read.

The master copy of this file is .claude/skills/customer-voice/SKILL.md on Crindo2/vault main. Other copies are taken from it unchanged.

The test

Read it aloud to one imagined reader who has the problem the text is about. If you would not say a sentence that way to their face, rewrite it. If the text only passes because every rule was satisfied, it has not passed.

How to write it

  1. Write for one reader in one situation. Start from the thing they most want to know and say it first.
  2. Compose the whole passage, then check it. Do not assemble it from separately written fragments.
  3. Use their facts: the insurer's name, their dates, their city. "Cigna confirmed yours complete on September 24" beats "the insurance company confirmed application complete".
  4. Join the reasoning. Words like because, so, which means and until carry the logic from one sentence into the next. A run of short declaratives with no connection between them is the clearest machine tell there is.
  5. Let sentences vary in length the way speech does. Contractions are fine.
  6. Say numbers and dates the way a person would: "five days past the deadline", "September 24".
  7. End on what to do next, once, in plain words.
  8. Keep every fact exact. Voice changes never change a number, a date, a source, a price or a legal reference.

What stays true from earlier rules

  • Say what we know and what follows from it, plainly. No caveat stacks, no hedging words, no method notes.
  • Name the source when a result rests on one (the statute, the insurer's own figure).
  • Each property's own rules still apply: identity separation, the helpline and no medical claims on health content, no refund sentence, approved offer wording that is marked as fixed.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 3d ago First seen · 77 lines · 62 tokens per session scan A d3d1eddf7b75

Subscribe to this mod's changes

customer-voice is a skill published in the GitHub repository Crindo2/gph-mcp-server (1 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 1,303 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-14.

Related

customer-voice compared with skills from other repositories

customer-voice next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
customer-voiceCrindo2/gph-mcp-serverSkill14d agoMITA62Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80ktodayMITA200Claude Code, Codex
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill196ktodayMITA53Claude Code, Codex