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.
git clone --depth 1 https://github.com/zircote/human-voiceWrote 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/plugins/zircote/human-voice/human-voice)<a href="https://agentmods.dev/plugins/zircote/human-voice/human-voice"><img src="https://agentmods.dev/badge/plugins/zircote/human-voice/human-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.
<a href="https://agentmods.dev/plugins/zircote/human-voice/human-voice"><img src="https://agentmods.dev/badge/plugins/zircote/human-voice/human-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
human-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 1mo 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.
What it actually says
{
"name": "human-voice",
"version": "0.8.3",
"description": "Detect AI-generated writing patterns and build authentic voice profiles through adaptive interviews and computational stylistics",
"author": {
"name": "zircote",
"url": "https://github.com/zircote"
},
"repository": "https://github.com/zircote/human-voice",
"homepage": "https://github.com/zircote/human-voice#readme",
"license": "MIT",
"keywords": [
"writing",
"ai-detection",
"content-quality",
"human-voice",
"markdown",
"documentation",
"voice-profile",
"interview-engine",
"stylometry",
"nlp"
]
}
What it installs
The manifest is a name and a version. 2 skills, 12 commands, 3 agents, 1 hook travel with it, and installing the plugin installs all of them — 460 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill human-voice A 66 tokens
- Skill voice A 65 tokens
- Command voice-profile A 11 tokens
- Command voice-review A 9 tokens
- Command voice-profiles A 16 tokens
- Command voice-drift A 30 tokens
- Command voice-setup A 10 tokens
- Command voice-interview A 12 tokens
- Command voice-resume A 12 tokens
- Command voice-sessions A 11 tokens
- Command voice-status A 12 tokens
- Command voice-copilot-install A 13 tokens
- Command voice-fix A 12 tokens
- Command voice-design A 16 tokens
- Agent interview-conductor A 61 tokens
- Agent profile-synthesizer A 56 tokens
- Agent voice-reviewer A 48 tokens
- Hook SessionStart A not measured
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.
- 1mo ago First seen · 25 lines scan A 72b28d9c493a
human-voice is a plugin published in the GitHub repository zircote/human-voice (12 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
story-skills marketplace
A suite of cross-referenced skills for end-to-end story writing and revision powered by markdown.
story-skills
A suite of cross-referenced skills and CLI maintenance tools for end-to-end fiction writing in markdown, in English or any other language. Covers premise development, story initialization, character management, worldbuilding, plot structure, theme, scene craft, outlined and discovery drafting, chapter writing…
unslop
Make assistant output sound human. Strip AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), engineer burstiness, restore voice. Preserves code, URLs, and technical accuracy.
unslop
Humanize assistant output. Strip AI-isms, engineer burstiness, preserve technical accuracy.
alive
Local, user-owned context for Claude Code. Keep your work in files you control.
arscontexta
Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets.