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 zajalist/hayba --skill hayba-dialogue-subtitle-reviewgit clone --depth 1 https://github.com/zajalist/haybaWrote 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/zajalist/hayba/hayba-dialogue-subtitle-review)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-dialogue-subtitle-review"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-dialogue-subtitle-review/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/zajalist/hayba/hayba-dialogue-subtitle-review"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-dialogue-subtitle-review.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 | $0.00029 | $0.00370 |
| Opus 5.5 | $0.00012 | $0.00148 |
| Sonnet 5.5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
hayba-dialogue-subtitle-review 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 13d 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.
What it actually says
Review one voiced dialogue beat
When to use
Use for a specific line or exchange with known voice asset, speaker, language, and intended duration. Record the subtitle text, reading-speed target, viewport sizes, and the moment the line should begin and end. Project dialogue and localization systems vary; identify the actual owner before editing.
Tool routing
- Inspect the sound with audio_asset_inspect and the subtitle widget with ui_get_widget_info. Measure the actual and longest expected line with ui_measure_text, then use ui_layout_snapshot, ui_render_widget_to_png, and ui_validate for clipping, safe areas, and contrast. Fix a confirmed layout problem with ui_set_slot_layout or ui_set_text_style, then re-render and revalidate.
- Check editor_get_state, start editor_start_pie only when a dialogue trigger exists, and observe live text with editor_pie_widget_tree and sound presence with audio_active_sounds. Capture the start, middle, and end through editor_pie_screenshot, polling each requested file. Stop with editor_stop_pie after this workflow's session.
- If the project has no typed dialogue or subtitle timing authoring path, make that edit in its own Unreal system and use this workflow for verification. Do not use 2D audio preview to claim spatial dialogue placement.
Evidence
Report text, language, voice asset, observed display interval, measured layout, validation findings, sound presence, and any timing mismatch. Active-sound presence does not prove lip sync, audibility, or exact subtitle synchronization; these need listened and viewed playback.
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.
- 13d ago First seen · 24 lines · 29 tokens per session scan A bfa1e1546c71
hayba-dialogue-subtitle-review is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 370 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
unreal-mcp
Automate Unreal Engine editor scenes, actors, and renders.
localize
Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.
maintaining-modding-environments
Use after first-run for ongoing modpack maintenance: update/install KB packs, author or register custom/mod KB packs, maintain localization glossary KBs for translator use, prune KB cache, health-check the environment, version-pin KB/tooling, or handle recurring BGS modding environment care.
using-bgs-translator
A translation workflow for Bethesda Game Studios plugins, which are game modification files such as .esp, .esm, and .esl. It prepares the plugin text for AI translation and exports files that xTranslator can use.
dialogue-systems
Build branching dialogue and narrative — a node/choice graph with conditions, variables, and localization hooks — and choose between authoring tools Ink and Yarn Spinner or a custom data-driven runner. Engine-neutral. Use when the user mentions dialogue system, branching dialogue, conversation tree, choices, Ink…
localization
Use when implementing localization (i18n/l10n) — TranslationServer, CSV/PO translation files, locale switching, RTL support, and pluralization in Godot 4.3+.