agentmods.dev

human-voice CLAUDE.md

human-voice CLAUDE.md is an instructions file for coding agents from zircote/human-voice. It costs 767 tokens per session, scanned A, original, MIT.

Project instructions for a Claude Code plugin that checks writing for signs of AI-generated language and builds a profile of a person’s writing style.

In plain words
What is it for?
Maintaining the plugin, reviewing or correcting writing style, running voice interviews, and managing voice profiles and review sessions.
Why use it?
They give the coding agent the project context, development rules, and commands needed to work on the plugin consistently.

Instructions file

not rated 10 1mo ago A scan 767 tokens original MIT
View the source file zircote/human-voice
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/claude-md
Clone the repo
git clone --depth 1 https://github.com/zircote/human-voice

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zircote/human-voice/claude-md.svg)](https://agentmods.dev/instructions/zircote/human-voice/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zircote/human-voice/claude-md"><img src="https://agentmods.dev/badge/instructions/zircote/human-voice/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 767 This file is loaded in full into every session.
When invoked 767 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 $0.00767 $0.00767
Opus 5 $0.00383 $0.00383
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00077 $0.00077

Measured 5d ago against content hash 4459a3b21535, 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 CLAUDE.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 5d 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.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Voice Plugin

A Claude Code plugin for detecting AI-generated writing patterns and building voice profiles through adaptive interviews and computational stylistics.

Branching Strategy

  • main: Stable release branch. Only merge from develop when the code is tested and reviewed. Do not commit directly to main.
  • develop: Active development branch. All new work goes here. Feature branches merge into develop. When develop is stable and ready for release, merge into main.

Project Context

This plugin provides:

  • Skills: human-voice (AI pattern detection), voice (voice elicitation interview)
  • Commands: /human-voice:voice-setup, /human-voice:voice-review, /human-voice:voice-fix, /human-voice:voice-interview, /human-voice:voice-profile, /human-voice:voice-resume, /human-voice:voice-drift, /human-voice:voice-sessions, /human-voice:voice-status
  • Agents: interview-conductor, profile-synthesizer, voice-reviewer
  • Scoring: Self-report scoring pipeline with SD cross-validation
  • NLP: Stylometric analysis pipeline (spacy-based)
  • Observer: Passive voice observation protocol via SessionStart hook

Development Guidelines

  • All development on the develop branch
  • Test commands locally with claude --plugin-dir .
  • Run scoring tests: python3 -m pytest scoring/tests/ -v
  • Validate character restrictions: node skills/human-voice/scripts/validate-character-restrictions.js docs/
  • Update CHANGELOG.md for user-facing changes
  • Keep backward compatibility (all features work without optional dependencies)

File Structure

.claude-plugin/plugin.json        # Plugin manifest (hooks registered here)
skills/human-voice/SKILL.md       # Core skill with detection patterns
skills/voice/SKILL.md            # Voice elicitation interview skill
commands/*.md                     # Slash commands
agents/*.md                       # Subagents (interview, synthesizer, reviewer)
hooks/hooks.json                  # SessionStart hook for observer protocol
templates/observer-protocol.md    # Observer protocol template
bin/                              # CLI tools (voice-session, voice-scoring, etc.)
question-bank/                    # Interview modules, schemas, scoring config
scoring/src/voice_scoring/       # Self-report scoring engine
nlp/src/voice_nlp/               # NLP stylometric analysis pipeline
lib/                              # Core library (session, branching, quality, etc.)
docs/                             # Documentation (Diataxis framework)
.github/agents/                   # GitHub Copilot custom agents
.github/workflows/                # CI workflows (validation, voice checks)

Read the full file on GitHub · 71 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. 5d ago First seen · 71 lines · 767 tokens per session scan A 4459a3b21535

Subscribe to this mod's changes

human-voice CLAUDE.md is an instructions file published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 767 tokens to every session, about $0.0038 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.

Writing and docsai-detectionclaude-codeclaude-code-plugincontent-qualitymarkdown
Related

Other instructions, from other repositories

unslop CLAUDE.md

Claude Code instructions for MohamedAbdallah-14/unslop, covering unslop — maintainer guide, readme is a product artifact, what this repo is, source of truth and mirrored locations (do not edit by hand).

MohamedAbdallah-14/unslop · 3,483 tokens

unslop AGENTS.md

AGENTS.md instructions for MohamedAbdallah-14/unslop, covering agent instructions — unslop repo, workflow, tone, commits and reviews.

MohamedAbdallah-14/unslop · 599 tokens

unslop copilot-instructions.md

Copilot instructions for MohamedAbdallah-14/unslop: When generating chat replies, code comments, or commit messages in this repository.

MohamedAbdallah-14/unslop · 401 tokens

unslop GEMINI.md

Gemini CLI instructions for MohamedAbdallah-14/unslop, covering unslop — gemini context, drop, keep, pattern and boundaries.

MohamedAbdallah-14/unslop · 349 tokens

skills CLAUDE.md

Instructions for skrrt-sh/skills, covering git workflow and repository structure.

skrrt-sh/skills · 1,061 tokens

documentation-review copilot-instructions.md

Instructions for zircote-plugins/documentation-review, covering copilot instructions, project overview, key components, plugin structure and development guidelines.

zircote-plugins/documentation-review · 272 tokens