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 LFTPadilla/agent-dev-kit --skill voice-studiogit clone --depth 1 https://github.com/LFTPadilla/agent-dev-kitWrote 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/lftpadilla/agent-dev-kit/voice-studio)<a href="https://agentmods.dev/skills/lftpadilla/agent-dev-kit/voice-studio"><img src="https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/voice-studio/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/lftpadilla/agent-dev-kit/voice-studio"><img src="https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/voice-studio.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 | $0.00032 | $0.00527 |
| Opus 5.5 | $0.00013 | $0.00211 |
| Sonnet 5.5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
voice-studio scanned grade A 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 26d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:3900/health What it actually says
VoiceStudio
Synthesize spoken audio responses and play expressive speech locally via GPU.
Usage
# Speak in background (non-blocking, default: explainer voice, 1.1x speed, 24 steps)
vsay -b "Task completed successfully."
# Expressive speech with pauses and non-verbal tokens
vsay -b "[surprise-wa] Incredible! The benchmark finished... [breathing] and ran fast. [laughter]"
Flags
-b, --bg: Play in background without blocking caller.-v <voice>:explainer(default),companion,enthusiast,narrator,radio,deep, or profile ID.-s <float>: Speed multiplier (default:1.1).-N <int>: Diffusion steps (default:24;16fast,32studio).--cfg <float>: Guidance scale (default:2.0).-o <path>: Save WAV to target file.--no-play: Generate audio without playing.-l <code>: Language code (default:es).-L, --list: List installed voice profiles.
Expressive Tokens & Prosody
Embed bracketed tokens for vocal inflections:
- Reactions:
[laughter],[surprise-wa],[surprise-ah],[sigh],[crying] - Hesitations & Feedback:
[uhm],[confirmation-en],[dissatisfaction-hnn],[shh],[cough] - Questions:
[question-en],[question-ah],[question-oh],[question-ei],[question-yi]
Pacing rules:
- Combine
...and[breathing]between clauses for natural breathing pauses. - Use punctuation marks (!, ?, ¡, ¿) to shape expressive pitch contours.
- Place commas before conjunctions to induce realistic pitch dips.
Health Check
curl -s http://127.0.0.1:3900/health
# Verify: "device": "cuda (AMD Radeon Graphics)"
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.
- 26d ago First seen · 50 lines · 32 tokens per session scan A 0ff346851efc
voice-studio is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 16d ago), licensed MIT. It adds 32 tokens to every session and 527 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.
Other skills, from other repositories
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.
compliance-checker
Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…
review-pr
Review a pull request for code quality and security issues. Use when the user wants to review a PR, check PR code changes, or audit a pull request. Triggers on: "review PR", "review pull request", "check this PR", "the review-pr skill".