voice-drift

voice-drift is a command for coding agents from zircote/human-voice. It costs 30 tokens per session (496 once invoked), scanned A, original, MIT.

A report that compares observed writing habits with a stored writing-style profile over time. It covers voice traits such as formality, tone, complexity, authority, and humor, plus selected writing mechanics.

In plain words
What is it for?
Use it to review confirmed voice patterns, detect drift from the profile, and identify areas that may need attention in future writing.
Why use it?
It shows where actual writing matches the profile and where it consistently differs, making gradual changes in writing style easier to notice.

Command

Part of the human-voice plugin — 2 skills, 12 commands, 3 agents, 1 hook shipped together

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 commands/zircote/human-voice/voice-drift
Clone the repo
git clone --depth 1 https://github.com/zircote/human-voice

Or install human-voice, the plugin that ships this one along with the rest of its 2 skills, 12 commands, 3 agents, 1 hook.

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 voice-drift

README.md
[![agentmods](https://agentmods.dev/badge/commands/zircote/human-voice/voice-drift.svg)](https://agentmods.dev/commands/zircote/human-voice/voice-drift)
Your own site
<a href="https://agentmods.dev/commands/zircote/human-voice/voice-drift"><img src="https://agentmods.dev/badge/commands/zircote/human-voice/voice-drift.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.00496
Opus 5 $0.00015 $0.00248
Sonnet 5 $0.00006 $0.00099
Haiku 4.5 $0.00003 $0.00050

Measured 5d ago against content hash 95e7865b0142, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

voice-drift 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.

commands/voice-drift.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice Drift Report

Generate a drift report comparing accumulated voice observations against the current profile.

Procedure

  1. Recall observations: Search Atlatl memory for voice observations:

    recall_memories(query="voice drift observed pattern writing", namespace="voice-observations", mode="hybrid")
    
  2. Load profile: Read ~/.human-voice/profile.json for current dimension scores. Extract the score for each dimension from the dimensions object. Do not use hardcoded values; every user's profile is different.

  3. Compare: For each observation, compare against the dimension scores loaded from the profile in step 2. Cover all gold standard dimensions (formality, emotional_tone, personality, complexity, audience_awareness, authority, narrativity, humor) and all gap dimensions that have scores. Also compare mechanics observations (contractions, Oxford comma, punctuation style) against the mechanics section of the profile.

  4. Report in three sections:

    Confirmed patterns: Observations that align with the profile. The user writes as the profile predicts.

    Drift detected: Observations that consistently diverge from the profile. Include the dimension name, the profile score, the observed tendency, the direction of drift (warmer, more formal, shorter sentences, etc.), and the number of observations supporting the pattern.

    New patterns: Voice characteristics observed that are not captured in the current profile at all.

  5. Recommend:

    • If no drift: "Profile remains accurate. No action needed."
    • If moderate drift (1-2 dimensions): "Consider updating the profile for [dimensions]. A targeted re-interview of [modules] would refine the scores."
    • If significant drift (3+ dimensions): "The profile may no longer represent your current voice. Consider a full re-interview with /voice-interview."
  6. If no observations exist: "No voice observations have been recorded yet. The observer protocol accumulates observations silently as you write during Claude Code sessions. Continue working and check back after you have authored several pieces of content."

Read the full file on GitHub · 40 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 · 40 lines · 30 tokens per session scan A 95e7865b0142

Subscribe to this mod's changes

voice-drift is a command published in the GitHub repository zircote/human-voice (10 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 496 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.

Related

Other commands, from other repositories