Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zircote/human-voice/plugin install 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/skills/zircote/human-voice/human-voice)<a href="https://agentmods.dev/skills/zircote/human-voice/human-voice"><img src="https://agentmods.dev/badge/skills/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/skills/zircote/human-voice/human-voice"><img src="https://agentmods.dev/badge/skills/zircote/human-voice/human-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.02306 |
| Opus 5.5 | $0.00026 | $0.00922 |
| Sonnet 5.5 | $0.00013 | $0.00461 |
| Haiku 4.5 | $0.00007 | $0.00231 |
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.
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Voice Skill
Detect, prevent, and correct AI-generated writing patterns to ensure authentic, professional human voice in all content.
Purpose
Ensure all published content reads as authentic human writing through:
- Detecting AI-telltale characters and patterns
- Identifying language-level AI indicators
- Correcting structural and stylistic issues
- Guiding content creation with human voice principles
Multi-Tier Analysis Framework
Tier 1: Character-Level Patterns (Automated)
Run automated character detection first. These patterns are strong AI indicators:
- Em dashes, en dashes, smart quotes
- Horizontal ellipsis, bullet characters
- Emojis and special Unicode characters
Execute validation:
node ${CLAUDE_PLUGIN_ROOT}/skills/human-voice/scripts/validate-character-restrictions.js <directory>
Auto-fix detected issues:
node ${CLAUDE_PLUGIN_ROOT}/skills/human-voice/scripts/fix-character-restrictions.js <directory>
For complete character patterns table, see references/character-patterns.md.
Tier 2: Language-Level Patterns (Manual Review)
Search for AI buzzwords and hedging phrases:
grep -rn -i -E "delve|realm|pivotal|harness|revolutionize|seamlessly" <directory>
grep -rn -i -E "it's worth noting|generally speaking|at the end of the day" <directory>
Key categories to check:
- Hedging phrases: "It's worth noting", "Generally speaking", "Arguably"
- AI buzzwords: delve, realm, pivotal, harness, revolutionize, seamlessly
- Filler phrases: "In order to", "Due to the fact that", "At this point in time"
- Excessive transitions: Furthermore, Moreover, Additionally, Consequently
For complete language patterns tables, see references/language-patterns.md.
Tier 3: Structural Patterns
Review content for these AI structural patterns:
- List addiction: AI formats everything as bullet lists when prose works better
- Rule of three overuse: AI over-applies rhetorical threes, making content predictable
- "From X to Y" construction: "From beginners to experts", "From setup to deployment"
- Monotonous sentence structure: Similar length and structure throughout
- Over-balanced perspectives: "On one hand... on the other hand" for everything
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 9.6 KB
- evals/fixtures/buzzword-heavy.md 878 B
- evals/fixtures/char-violations.md 369 B
- evals/fixtures/clean-content.md 592 B
- evals/fixtures/mixed-issues.md 953 B
- evals/fixtures/partial-char-violations.md 638 B
- evals/fixtures/structural-issues.md 1.1 KB
- evals/fixtures/voice-issues.md 1023 B
- examples/before-after.md 8.1 KB
- references/character-patterns.md 3.9 KB
- references/language-patterns.md 6.1 KB
- references/structural-patterns.md 6.1 KB
- references/voice-patterns.md 7.3 KB
- scripts/fix-character-restrictions.js 8.0 KB runs code
- scripts/validate-character-restrictions.js 9.3 KB runs code
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 · 270 lines · 66 tokens per session scan A 2993d9c15831
human-voice is a skill published in the GitHub repository zircote/human-voice (12 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 2,306 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
revision-continuity
This skill should be used when the user asks to "revise a chapter", "continuity check", "find inconsistencies", "audit character state", "check timeline consistency", "developmental edit", "structural revision", "reverse outline", "cut a subplot", "revision passes", "what pass next", "pacing check" as a revision pass…
story-maintenance
This skill should be used when the user asks to "validate", "reindex", "repair registries", "check links", "run the continuity, pacing, clue, voice, or name checks", "count words", "summarize a story project", "import an existing manuscript", "export a manuscript", "run a build", "generate a diagram", "record…
feedback-triage
This skill should be used when the user asks to "process beta reader feedback", "alpha reader feedback", "feedback round", "synthesize reader feedback", "reader notes", "beta feedback", "reader readiness check", "review copy", "send the draft to readers", "share with readers who don't use GitHub", "triage the reader…
publishing
This skill should be used when the user asks to "self-publish", "publish my book", "ISBN", "copyright page", "book metadata", "BISAC", "keywords", "KDP", "IngramSpark", "Draft2Digital", "go wide", "Kindle Unlimited", "print interior", "trim size", "paperback", "ebook", "EPUB", "cover wrap", "spine width", "pricing"…
story-init
This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story", or wants to begin a new fiction writing project from scratch. NOT for a sequel or prequel (use series-continuity), or for finding the idea before a project exists (use…
worldbuilding
This skill should be used when the user asks to "create a location", "add a location", "magic system", "political system", "build the world", "add culture", "world history", "technology system", "religion", "economy", "map", "travel times", "routes", "calendar", "moons", "seasons", "naming language", "conlang names"…