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-playgit 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-play)<a href="https://agentmods.dev/skills/zhitongblog/unflick/unflick-play"><img src="https://agentmods.dev/badge/skills/zhitongblog/unflick/unflick-play/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-play"><img src="https://agentmods.dev/badge/skills/zhitongblog/unflick/unflick-play.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 | $0.00096 | $0.00784 |
| Opus 5.5 | $0.00038 | $0.00314 |
| Sonnet 5.5 | $0.00019 | $0.00157 |
| Haiku 4.5 | $0.00010 | $0.00078 |
Grade A, and why
unflick-play 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unflick: play & control video
You drive the unflick video player. Prefer the MCP tools
when the unflick MCP server is connected; otherwise shell out to the unflick
CLI (every tool has a 1:1 command).
Core flow
- Open —
play(file=<path-or-url>).fileaccepts a local path or a streaming URL (yt-dlp resolves YouTube/Bilibili/Twitch/Vimeo and 26 others). Optionalseek(seconds),volume(0–100),speed(e.g.1.5). - Control —
pause,resume,stop,seek(seconds),set_volume(level),set_speed(rate). - Inspect —
get_statusreturns{state, file, position, duration, volume, speed}. Read theunflick://now-playingresource for the same data when you just need a snapshot.
CLI equivalents
unflick play "https://youtu.be/dQw4w9WgXcQ" --volume 80 --speed 1.25
unflick seek 120 # jump to 2:00
unflick pause
unflick status # JSON to stdout
Beyond a file path
- Discs —
disc_list()reports optical drives and what is in them;playtakes a.iso, a folder withVIDEO_TS, a drive path, ordvd://3for a specific title. Clipping and hover previews are refused on a disc, by design. - A television —
cast(action="list")finds DLNA renderers on the network,cast(action="to", renderer=…)sends what is playing, and pause/resume/seek/ stop drive it from there. - The window —
window_mode(mode="normal"|"pip"|"music"). It answers "no window" when only the headless daemon is running, rather than pretending. - Getting back —
session()reports what was last watched and how far in;session(action="restore")reopens it.recent_files()is the list. - What is playing —
now_playing()gives title/artist/album and whether there is picture at all, whichget_status(path, position, state) does not.
Guidance
- To "skip ahead 30s", read
get_status.position, thenseek(position + 30). - Speed lives in
0.25–4.0in practice; volume is0–100. - If a URL fails, it's usually a missing/old
yt-dlp— surface the error text rather than retrying blindly. - Resume: before playing a file you've seen before,
get_position(path)and pass it asseek; after stopping,save_position(path, position).
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 · 61 lines · 96 tokens per session scan A 5d74c745444f
unflick-play is a skill published in the GitHub repository zhitongblog/unflick (1 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 784 once invoked, about $0.0004 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-play compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unflick-playzhitongblog/unflick | Skill | 1 | 1mo ago | MIT | A | 96 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |