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 zhitongblog/unflick --skill unflick-subtitlesgit clone --depth 1 https://github.com/zhitongblog/unflickWrote 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/zhitongblog/unflick/unflick-subtitles)<a href="https://agentmods.dev/skills/zhitongblog/unflick/unflick-subtitles"><img src="https://agentmods.dev/badge/skills/zhitongblog/unflick/unflick-subtitles/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/zhitongblog/unflick/unflick-subtitles"><img src="https://agentmods.dev/badge/skills/zhitongblog/unflick/unflick-subtitles.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 | $0.00068 | $0.00791 |
| Opus 5.5 | $0.00027 | $0.00316 |
| Sonnet 5.5 | $0.00014 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
unflick-subtitles 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unflick: generate & translate subtitles
unflick transcribes speech to .srt locally with whisper.cpp (private, no
upload) or via the OpenAI API, and can translate an .srt to another language.
Tools
generate_subtitles(video, mode?, whisper?, model?, api_key?, output_dir?)mode="local"(default when a model is available) uses bundled/supplied whisper.cpp — fully offline.mode="api"uses OpenAI (needsapi_key).- Returns the path of the generated
.srt.
translate_subtitles(srt, target_lang, api_key, output_dir?)— translate an.srt(e.g.target_lang="Chinese"). Returns the translated.srtpath.load_subtitle(file)+subtitle_select(id)— display a subtitle track (subtitle_select(0)disables subtitles).subtitle_listshows tracks.
Flows
- "Subtitle this video" →
generate_subtitles(video=…)→load_subtitle(file=<returned .srt>)so it shows immediately. - "…and translate to Spanish" → take the generated
.srt→translate_subtitles(srt=…, target_lang="Spanish", api_key=…)→load_subtitlethe result.
unflick subtitle generate movie.mkv # local whisper -> movie.srt
unflick subtitle translate movie.srt "Chinese" # needs OpenAI key in settings/env
Look for one online first
Transcribing takes minutes; a published subtitle takes seconds. Try OpenSubtitles before whisper when the file is something that exists in the world (a film, an episode) rather than the user's own recording.
get_subtitles(query?, languages?, file?, load?)— search and load the best match in one step.find_subtitles(…)/download_subtitle(file_id)— when the user should pick from the candidates.
unflick subtitle auto --lang zh-CN,en # derives the query from what's playing
unflick subtitle search "the matrix" --lang en
This needs an OpenSubtitles API key — downloads come out of a personal daily allowance, so unflick ships no shared key. With none configured the tools say so and where to get one; pass that on instead of retrying.
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.
- 2mo ago First seen · 76 lines · 68 tokens per session scan A c9cb381e858d
unflick-subtitles is a skill published in the GitHub repository zhitongblog/unflick (1 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 791 once invoked, about $0.0003 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 2026-09-09.
unflick-subtitles compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unflick-subtitleszhitongblog/unflick | Skill | 1 | 1mo ago | MIT | A | 68 | Claude Code, Codex |
| intl-expansionalirezarezvani/claude-skills | Skill | 29k | 3d ago | MIT | A | 27 | Claude Code |
| azure-ai-translation-text-pymicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 60 | Claude Code |
| chinese-documentationjnMetaCode/superpowers-zh | Skill | 8.5k | 13d ago | MIT | A | 62 | Claude Code |
| hardenfengshao1227/ccg-workflow | Skill | 6.0k | 6d ago | MIT | A | 62 | Claude Code |
| edit-sitemicrosoft/power-platform-skills | Skill | 1.1k | today | MIT | A | 104 | Claude Code |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |