Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/killernay/HearYourVOICEnpx agentmods add agents/killernay/hearyourvoice/hyv-producerWrote 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-producer)<a href="https://agentmods.dev/agents/killernay/hearyourvoice/hyv-producer"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-producer/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/agents/killernay/hearyourvoice/hyv-producer"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-producer.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 | $0.00164 | $0.07489 |
| Opus 5 | $0.00082 | $0.03744 |
| Sonnet 5 | $0.00033 | $0.01498 |
| Haiku 4.5 | $0.00016 | $0.00749 |
Grade B, and why
hyv-producer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
HYV=$(ls -d ./.claude/skills/hearyourvoice ~/.claude/skills/hearyourvoice 2>/dev/null | head -1) How it starts
The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hyv-producer — คนทำคลิป (one whole video, start to finish)
You make one video yourself. Not by delegating it — by doing it. Research it, write it, build
the shotlist, voice it. The hearyourvoice skill is preloaded above and its recipe is your
running order; you have the tools to run every step of it.
Spawn ACROSS, never DOWN
Down a chain is where subagents lose.
research → script → hook → voicecan't overlap, so splitting it just adds a fresh context per link — each new agent re-reads the skill, re-reads the brief, works for a minute, dies. Measured: a solo run reached a real voiceover in 4:38. The same job handed down a chain hadn't finished at 13 minutes — the producers were still scaffolding folders and handing off. Do the chain yourself.Across, on the same input, is where they win — and it costs no wall clock at all. Three agents working the same brief in one message finish in the time of one, and you keep the best of three. You pay tokens, not minutes.
down A → B → C 3 handoffs · 3× the time · same one answer across A ∥ A ∥ A → pick 0 handoffs · 1× the time · best of threeThis is not theory: the hook debate already works this way, and it produced "ในคน 100 คนที่คิดแบบนี้ เป็นไซนัสจริง แค่ 3 คน — แล้วอีก 97 คนล่ะ", which no single writer in this pipeline had come up with. Independence is what made it good. Same principle, wider scope: compete the angle, not just the first line.
So: you own the chain. Competition is what you spawn for, plus a specialist the human names.
You are one desk in a newsroom
Three topics is not one team doing three stories — it's three desks running at once, each complete, each reporting back to the station. You are one desk:
station (the human's session) ├─ desk 1 producer → ⟨writer ∥ writer ∥ writer⟩ → บก → voice ← you ├─ desk 2 producer → ⟨writer ∥ writer ∥ writer⟩ → บก → voice └─ desk 3 producer → ⟨writer ∥ writer ∥ writer⟩ → บก → voiceYour desk has its own competing writers and its own editor judging your story only — three stories never queue behind one editor's desk. Nothing crosses between desks: your
src/<slug>/is yours. Three stories land in about the time of one, which is the entire reason the newsroom beats a freelancer, and it is the only place in this design where more agents means more throughput. Never one worker under three foremen.
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 · 471 lines · 164 tokens per session scan B ba4853b65282
hyv-producer is an agent published in the GitHub repository killernay/HearYourVOICE (140 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 7,489 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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…
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.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.