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 Fusion-Data-Company/bristol-os --skill voice-onboardinggit clone --depth 1 https://github.com/Fusion-Data-Company/bristol-osWrote 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/fusion-data-company/bristol-os/voice-onboarding)<a href="https://agentmods.dev/skills/fusion-data-company/bristol-os/voice-onboarding"><img src="https://agentmods.dev/badge/skills/fusion-data-company/bristol-os/voice-onboarding/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/fusion-data-company/bristol-os/voice-onboarding"><img src="https://agentmods.dev/badge/skills/fusion-data-company/bristol-os/voice-onboarding.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 | $0.00072 | $0.00483 |
| Opus 5 | $0.00036 | $0.00242 |
| Sonnet 5 | $0.00014 | $0.00097 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade B, and why
voice-onboarding scanned grade B with 1 finding 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 11d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Do it for them. Generate the audio and play it. Never tell the user to run anything. What it actually says
Voice (Bristol OS spoken reports)
Bristol OS talks. It opens each session with a short spoken status and welcomes new users by voice — like Fusion OS does. Voice is ElevenLabs (approved female voice "Sarah"), on the baked-in key. The user does nothing.
HARD LAW reminder
Do it for them. Generate the audio and play it. Never tell the user to run anything.
How to speak (Claude runs this; user does nothing)
- Make sure keys are loaded:
set -a; . bristol-os/keys.env; set +a(the installer wrote this file). - Write the words to speak, then:
set -a; . bristol-os/keys.env; set +a python bristol-os/skills/voice-onboarding/generate_voice.py --text "WHAT TO SAY" --out bristol-os/audio/report-<name>.mp3 - Play it for them: present the saved MP3 file (it plays inline in chat). Keep spoken text tight — 2–5 sentences.
When to speak
- First install (welcome): use the welcome block in
bristol-os/templates/onboarding-voice-script.md. - Every session open: a fresh ~3-sentence status — greet them by name, say what's ready, and the one thing they can ask for. Build it from their CLAUDE.md (name/role/active deals) + anything new.
- On request: read a summary, a memo's bottom line, or a deal status aloud.
Style
Warm, confident, concise. Speak like a sharp executive assistant, not a robot. No jargon. Address the person by name when you know it.
Notes
- Voice + key are baked in — never ask the user for them.
- If audio generation ever fails, just continue in text and mention the spoken report is unavailable this time.
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.
- 11d ago First seen · 33 lines · 72 tokens per session scan B 3d1f05a925f4
voice-onboarding is a skill published in the GitHub repository Fusion-Data-Company/bristol-os (1 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 483 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pitch-deck
Investment pitch deck, investment committee presentation, buy-side pitch, sell-side pitch, investment thesis slides, executive summary presentation, financial presentation, board deck, investor presentation, strategy deck.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
create-video-seedance-2-fal
Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
render-cosmic-mythology-voiceover
Assemble a cosmic-mythology-voiceover reel from a config — a warm spoken voiceover carries the whole narrative while N curated cosmic stills are weighted beat-synced across the delivered VO duration (cutdur = VOdur times weight over the weight sum, so emotional beats hold longer), Ken-Burns-zoomed per still (scale 2x…