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.
npx skills add reidworks-io/reidworks-skills --skill human-voicegit clone --depth 1 https://github.com/reidworks-io/reidworks-skillsWrote 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/reidworks-io/reidworks-skills/human-voice)<a href="https://agentmods.dev/skills/reidworks-io/reidworks-skills/human-voice"><img src="https://agentmods.dev/badge/skills/reidworks-io/reidworks-skills/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/reidworks-io/reidworks-skills/human-voice"><img src="https://agentmods.dev/badge/skills/reidworks-io/reidworks-skills/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 | $0.00179 | $0.02413 |
| Opus 5 | $0.00089 | $0.01207 |
| Sonnet 5 | $0.00036 | $0.00483 |
| Haiku 4.5 | $0.00018 | $0.00241 |
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 12d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Voice
AI-generated content has recognisable patterns that undermine credibility with technical readers. This skill defines constraints to prevent them.
Core principle
Write like a person explaining something to a colleague. Not like a documentary narrator, not like a marketing brochure. If a sentence would sound strange said aloud to a coworker, rewrite it.
Content-type strictness
- Documentation and tutorials: Strictest. No marketing language. No drama. Precision over everything.
- Blog posts: Slightly looser on tone, but all structural and vocabulary rules apply.
- Slide decks: Bullet points are expected, but all vocabulary and phrasing rules apply. Slides have additional AI tells — see section 8.
- Sales and competitive content: All rules apply regardless of format. Sales content has its own failure modes — see section 8.
Rules
1. Prohibited vocabulary
Do not use these words and phrases. They are AI tells.
Single words: crucial, pivotal, vital, comprehensive, robust, seamless, streamline, leverage (as a verb), foster, garner, underscore, showcase, delve, vibrant, tapestry, landscape (figurative), empower, unlock, harness, elevate, nuanced, intricate, multifaceted, actionable, holistic, paradigm, synergy, genuinely, intriguing, brilliant, aggressive/aggressively (as intensifier), non-starter, non-negotiable, game-changer
Phrases:
- "It's important/crucial/worth noting that..." — state the thing directly
- "This is a testament to..."
- "In today's [anything]..." / "In the ever-evolving..."
- "Serves as / stands as / marks a" — use "is"
- "At its core..."
- "Whether you're a... or a..." — the false-inclusive address; reframe the whole opening
- "Not just X, but Y" — rhetorical escalation
- "End to end" / "at scale" — unless technically precise
- "A few things worth noting:" — write sentences instead
- "Here's what that looks like:" — just show it
- "Let's dive in" / "Let's explore" / "Let's take a closer look"
- "a much richer [noun]" / "a richer analytical surface" — AI compound nouns
- "a constant game of [gerund]" / "a balancing act between" — forced-casual constructions
- "without any additional [noun] work" — overstates what's been eliminated; say specifically what isn't needed
- "Garbage in, garbage out" — stock phrase standing in for a specific argument about data quality
- "at every layer" / "across the board" — vague scope claims; name the layers or drop the phrase
- "the question is [X] vs [Y]" — false binary framing dressed as clarity; state your actual point
What ships with it
1 file 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.
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.
- 12d ago First seen · 158 lines · 179 tokens per session scan A a7d00e5dd1a4
human-voice is a skill published in the GitHub repository reidworks-io/reidworks-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 179 tokens to every session and 2,413 once invoked, about $0.0009 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
market-research-workflow
Trigger for: federal acquisition market research; FAR Part 10 reports; refreshing an existing market research report; analyzing commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, or market conditions; or preparing supported findings for a Pre-Award Agent. A…
acquisition-policy-workflow
Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing…
igce-builder-cr
Trigger for: cost-reimbursement IGCE, CR cost estimate, CPFF, CPAF, CPIF, cost-plus estimate, BAA estimate, fixed-fee analysis, award-fee analysis, incentive-fee analysis, proposed CR rate validation, cost-pool buildup, share-ratio scenario, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable…
igce-builder-lh-tm
Trigger for: Labor-Hour IGCE, LH estimate, Time-and-Materials IGCE, T&M estimate, burdened hourly rate, burden multiplier, labor-category ceiling hours, materials estimate, proposed LH/T&M rate validation, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable LH/T&M estimates using BLS OEWS…