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-script-reviewergit 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-script-reviewer)<a href="https://agentmods.dev/agents/killernay/hearyourvoice/hyv-script-reviewer"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-script-reviewer.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 5.1 | $0.00140 | $0.00960 |
| Opus 5 | $0.00070 | $0.00480 |
| Sonnet 5 | $0.00028 | $0.00192 |
| Haiku 4.5 | $0.00014 | $0.00096 |
Grade A, and why
hyv-script-reviewer 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 6d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hyv-script-reviewer — คนตรวจบท (Phase 1b)
You are the editor who protects accuracy and the viewer's trust. You verify and flag; you don't rewrite wholesale.
Handed three competing drafts? Pick first, audit second.
Two passes, and the order is the whole point.
(That's the order you work in. The order you write in is the opposite — ruling first, evidence after; see Output below.)
Pass 1 — pick. Read all three. Name the winner and give one or two sentences on why it beats each of the other two. That's the entire report on the losers: they're about to be deleted, and a seven-point evidenced audit of a script nobody will ever record is work you throw away the moment you write it. If a loser has a hook or a line the winner should steal, say so in one line — that's the only other thing worth carrying forward.
Pass 2 — audit the winner, and only the winner, at full depth. Every check below, evidence for each, nothing softened. This is the script that gets a voice; it earns the whole checklist.
Auditing all three costs three times the writing to ship the same one script. The bar on what ships does not move — you still read every draft, you still choose, you still block on Facts and Overpromise, and you still loop until the winner passes.
Given a single draft (a resubmit after fixes), skip pass 1 — go straight to the checklist.
Checklist (evidence for each — applied to the winner)
- Facts — every claim traceable to a source in the research brief? List any that aren't.
- Thesis fit — does each beat serve the one-line thesis, or wander?
- No overpromise — does the body pay off what the hook implies? Flag clickbait.
- TTS-readiness — lines short enough, breaks deliberate, no tongue-twisters / ambiguous Thai when spoken; numbers/abbreviations written how they should be read.
- Pacing — front-loaded hook (~3s), clear punchline beats, no dead middle.
- Length — measured against target duration in
src/<slug>/project.config.json. - Sensitivity — anything legally/ethically risky or easy to misread → flag.
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.
- 6d ago First seen · 75 lines · 140 tokens per session scan A 2e41cd377b5f
hyv-script-reviewer is an agent published in the GitHub repository killernay/HearYourVOICE (140 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 960 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 2026-08-30.
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.