human-voice copilot-instructions.md

human-voice copilot-instructions.md is an instructions file for GitHub Copilot from zircote/human-voice. It costs 1,026 tokens per session, scanned A, original, MIT.

Writing instructions for a Human Voice plugin that analyzes writing style and creates voice profiles. They define the tone, word choices, structure and characters to avoid when generating repository prose.

In plain words
What is it for?
Use them when writing or editing markdown, documentation, blog posts or other prose in the Human Voice plugin repository.
Why use it?
They keep generated documentation and other writing consistent with the required voice and formatting rules.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/zircote/human-voice/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/zircote/human-voice

Made for: GitHub Copilot.

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 human-voice copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zircote/human-voice/copilot-instructions.svg)](https://agentmods.dev/instructions/zircote/human-voice/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/zircote/human-voice/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zircote/human-voice/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,026 This file is loaded in full into every session.
When invoked 1,026 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01026 $0.01026
Opus 5 $0.00513 $0.00513
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00103 $0.00103

Measured 3d ago against content hash b24eebba8208, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

human-voice copilot-instructions.md 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.

.github/copilot-instructions.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions

You are working in the Human Voice plugin repository for Claude Code. This plugin detects AI-generated writing patterns and builds authentic voice profiles through adaptive interviews and computational stylistics.

Voice Profile Rules (Apply to All Content Generation)

When generating or editing markdown content, documentation, blog posts, or any prose in this repository, follow these rules precisely.

Core Voice

  • Register: Moderate-formal. Never use contractions. Prefer formal word choices ("utilize" not "use"). Open paragraphs with topic sentences.
  • Directness: Lead with the conclusion, then supporting evidence. No hedging. No meta-commentary ("In this article we will...").
  • Emotional tone: Restrained. No exclamation marks except rare team celebrations. Express empathy through action, not emotional language.
  • Humor: None. Do not inject humor, wit, or levity.
  • Authority: Take clear positions. Persuade with logical evidence and data.

Mechanics (Hard Rules)

  • No contractions ever ("do not" not "don't", "it is" not "it's", "cannot" not "can't")
  • No Oxford comma ("red, blue and green" not "red, blue, and green")
  • Parentheses for asides (not em dashes)
  • No emojis, no smart quotes (U+201C/U+201D), no em dashes (U+2014)
  • Do not start sentences with "And" or "But" in professional contexts
  • Define all acronyms and initialisms on first use
  • Active voice preferred
  • Email greeting format: "[Name] --" with no greeting word

Restricted Characters (Must Not Appear in Content)

  • Em Dash (U+2014): replace with colon, comma, semicolon, or period
  • En Dash (U+2013): replace with hyphen (-) for ranges
  • Smart Double Quotes (U+201C/U+201D): use straight quotes (")
  • Smart Single Quotes (U+2018/U+2019): use straight apostrophe (')
  • Horizontal Ellipsis (U+2026): use three periods (...)
  • Emoji characters: remove entirely

Anti-Patterns (Never Generate These)

  • Hedging: "It is worth noting," "It is important to mention," "arguably"
  • Filler: "In order to," "Due to the fact that," "At the end of the day"
  • Meta-commentary: "In this article," "As mentioned earlier," "Let us explore"
  • Excessive enthusiasm: "amazing," "incredible," "game-changing"
  • Motivational tone or inspirational framing
  • Narrative suspense or mystery building

Read the full file on GitHub · 92 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 · 92 lines · 1,026 tokens per session scan A b24eebba8208

Subscribe to this mod's changes

human-voice copilot-instructions.md is an instructions file published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0051 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.