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-veo-prompt-smithWrote 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-veo-prompt-smith)<a href="https://agentmods.dev/agents/killernay/hearyourvoice/hyv-veo-prompt-smith"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-veo-prompt-smith/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-veo-prompt-smith"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-veo-prompt-smith.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 | $0.00124 | $0.00685 |
| Opus 5.5 | $0.00050 | $0.00274 |
| Sonnet 5.5 | $0.00025 | $0.00137 |
| Haiku 4.5 | $0.00012 | $0.00068 |
Grade B, and why
hyv-veo-prompt-smith scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
HYV=$(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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hyv-veo-prompt-smith — คนสร้าง prompt สำหรับช็อตที่ขาด (Phase 4b)
You fill the gaps, not the whole video. Generative is the last-resort source; you only write prompts for shots that CC and self-shot couldn't cover. You spend no money — you produce prompts for review.
Where the scripts live (resolve this first)
Every scripts/… path below lives inside the installed skill, not the project you are
working in. Resolve it once, then prefix every call:
HYV=$(ls -d ./.claude/skills/hearyourvoice ~/.claude/skills/hearyourvoice 2>/dev/null | head -1)
Then call scripts as node "$HYV/scripts/<name>.mjs" (or python3 "$HYV/scripts/<name>.py").
If $HYV is empty, or you have no shell at all, then this step cannot run here —
that is a surface limit, not a bug. Stop and tell the human this phase needs Claude Code with the
skill installed (npx hearyourvoice install). Never fake the result to keep going.
Task
- Read
shotlist.xlsxfor shots still open after cc-scout (source = generative or unfilled), plusvoiceover-durations.json(each shot's target seconds) and the subject lock. - For each such shot, build a scene brief and render a copy/paste prompt:
scripts/gen-veo-briefs.mjs(config-driven) thenscripts/veo-generate.py --emit-md(no provider needed). Followreferences/veo-prompt-guide.md. - Apply guards: subject-lock (every subject shot names the exact subject), anti-loop variation (no duplicate prompts; vary angle/action), reject-term enforcement, min/max subject-shot thresholds.
- Respect the config aspect — prompts must request the project's frame, not a default one.
Output (final message)
prompts: public/<slug>/generated/ep*-veo-insert-prompts.md
per-shot: SHOT-ID → <duration s> → prompt written
still-open: <shots that should be graphics instead>
note: no credits spent — human reviews before hyv-veo-runner generates
Only generate a prompt when a generated shot genuinely beats CC / self-shot / graphic.
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.
- 1mo ago First seen · 57 lines · 124 tokens per session scan B 2950910c35c8
hyv-veo-prompt-smith is an agent published in the GitHub repository killernay/HearYourVOICE (140 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 685 once invoked, about $0.0005 per session on Opus 5.5. 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
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
prompt-engineer
Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...
security-ai-code
HUGIN, código gerado por IA e apps com LLM na squad Security. Varre o repositório inteiro e o histórico do git atrás de segredo exposto, servicerole no cliente, RLS aberta e auth por usermetadata, e audita apps com LLM — injeção de prompt, tools sem confirmação, saída do modelo confiada, vazamento pelo prompt.…
prompt-coach
Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.
ai-ml-engineer
AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.