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.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01153 |
| Sonnet 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 8d 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.
- 8d 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 (10 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 2,306 once invoked, about $0.0003 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.
Other skills, from other repositories
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.