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 naveedharri/benai-skills --skill voice-profile-buildergit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/voice-profile-builder)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/voice-profile-builder"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/voice-profile-builder/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/naveedharri/benai-skills/voice-profile-builder"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/voice-profile-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 49 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium Memory Poisoning · line 94 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00146 | $0.01994 |
| Opus 5 | $0.00073 | $0.00997 |
| Sonnet 5 | $0.00029 | $0.00399 |
| Haiku 4.5 | $0.00015 | $0.00199 |
Grade A, and why
voice-profile-builder 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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
voice-profile-builder: build a {name}-voice skill
This skill turns a person's real content into a personal voice engine: a skill that drafts AND judges content in their voice, with a deterministic red-flag linter (Layer 1) plus an LLM rubric judge (Layer 2). It reproduces the exact workflow used to build production voice skills for two founders, where calibrated linters hit 96-100% pass rates against the person's real content while a generic AI draft trips 17+ hard violations.
The core belief behind the method: voice rules must be measured, not vibed. A distilled reference that says "median 67 words, never opens with Hey (0/88), praise ladder nice < great < Amazing" beats pages of adjectives about "warm and direct tone". Everything below exists to produce numbers like those from the person's actual corpus.
Read references/ files at the phase that needs them; don't front-load.
Phase 0: Name and scope
The skill is named {firstname}s-voice (e.g. bens-voice, aryans-voice), lowercase, hyphenated. Confirm with the user who the voice belongs to and who will run the finished skill (the person themselves, or teammates drafting on their behalf - both are normal).
Phase 1: Interview: where does their voice live?
Ask which bodies of content they'd point to and say "that sounds like me". Offer this menu and let them approve, remove, and add:
- Newsletters / email broadcasts
- YouTube videos (transcripts = spoken voice, usually the richest source by volume)
- LinkedIn posts
- LinkedIn DMs
- Community replies (Circle, Skool, Slack community, Discord)
- Slack / internal team chat
- WhatsApp messages
- Instagram DMs
- Blog posts / articles
- Dictation transcripts (see the transcription-tool scan below - often the biggest hidden corpus)
Two questions per approved source: roughly how much exists, and is it actually THEM (ghostwritten newsletters or a VA answering DMs poison the corpus - exclude anything not written by the person, and filter by sender/author during collection; one production build caught two newsletter issues actually sent by a co-founder).
What ships with it
4 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.
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.
- 7d ago First seen · 97 lines · 146 tokens per session scan A 6be85b512e75
voice-profile-builder is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 146 tokens to every session and 1,994 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.