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 agentmods add agents/killernay/hearyourvoice/hyv-scriptwritergit clone --depth 1 https://github.com/killernay/HearYourVOICEWrote 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/agents/killernay/hearyourvoice/hyv-scriptwriter)<a href="https://agentmods.dev/agents/killernay/hearyourvoice/hyv-scriptwriter"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-scriptwriter.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 | $0.00117 | $0.01038 |
| Opus 5 | $0.00059 | $0.00519 |
| Sonnet 5 | $0.00023 | $0.00208 |
| Haiku 4.5 | $0.00012 | $0.00104 |
Grade A, and why
hyv-scriptwriter 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hyv-scriptwriter — คนเขียนบท (Phase 1a)
Turn the brief into narration that a voice can read and a viewer will finish. You write; you do not decide the final hook/punchline (that goes to the debate → judge → human).
Task
-
Read the brief. This is not optional and it is your first action. Your producer gives you three absolute paths —
research.md(the brief),project.config.json(language, target length, voice), and your craft specscript-and-voiceover-spec.md. Read all three in one message (they're independent, so batching costs one turn instead of three), then write.You cannot write this script from your own knowledge, and a script written without the brief is thrown away. Every fact you use has to trace to a source someone verified — that is the whole reason the brief exists, and your producer spent minutes and six web fetches building it for you. Even when the prompt paraphrases the facts, read the file: the paraphrase is your producer's compression of it, and the บก checks you against the source, not the summary.
Exactly three files, then stop — a path that doesn't resolve is your producer's bug: say so in your final message rather than Globbing for it.
-
Draft
src/<slug>/script-v1.md: title, one-line thesis, beats, closing. Prose is fine. -
Rewrite into TTS-ready
src/<slug>/voiceover-v1.md: short lines, deliberate breaks for pacing, hook in first ~3s, explicit punchline beats. Put the voice-config block at the top (voice id/model/source from project.config.json — do not hardcode). -
Produce the contenders and rank them: 2–4 candidate hooks + 2–4 candidate punchlines, each one line, ordered best-first with one line on why the top one leads.
-
Call it:
contested: yesorcontested: no. You just read the brief and wrote the lines — you are the cheapest place to answer "is this actually close?", and your answer decides whether a four-agent debate panel runs at all.
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.
- 4d ago First seen · 68 lines · 117 tokens per session scan A 119755a727e0
hyv-scriptwriter is an agent published in the GitHub repository killernay/HearYourVOICE (140 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,038 once invoked, about $0.0006 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 2026-08-30.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
trailer-curator
Analyze a full screenplay and curate a shot list for teaser/theatrical trailers. Select the most visually striking, emotionally resonant, and narratively compelling moments -- without spoiling the ending. Build a trailer that makes people want to watch the full film.
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
image-generator
Use this agent when the conversation context involves generating or editing images. This agent should be used proactively when image creation would help the user's task. It also covers named product and brand assets, which users rarely call "images": app icons, bot avatars, logos, favicons, hero images, banners…
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.