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 jianshuo/claude-skills --skill wjs-burning-subtitlesgit clone --depth 1 https://github.com/jianshuo/claude-skillsWrote 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/jianshuo/claude-skills/wjs-burning-subtitles)<a href="https://agentmods.dev/skills/jianshuo/claude-skills/wjs-burning-subtitles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-burning-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/jianshuo/claude-skills/wjs-burning-subtitles"><img src="https://agentmods.dev/badge/skills/jianshuo/claude-skills/wjs-burning-subtitles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 67 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00153 | $0.03297 |
| Opus 5 | $0.00077 | $0.01648 |
| Sonnet 5 | $0.00031 | $0.00659 |
| Haiku 4.5 | $0.00015 | $0.00330 |
Grade A, and why
wjs-burning-subtitles scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL -o /tmp/ff.zip https://evermeet.cx/ffmpeg/getrelease/zip How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wjs-burning-subtitles
Video + SRT → video with subtitles. Also the final-encode stage for the localization pipeline: takes a video, an optional dub track from /wjs-dubbing-video, and an optional SRT to burn, and produces the upload-ready MP4 in one ffmpeg pass. No cascade of decodes/re-encodes.
When to use
- User has an SRT and wants it always-visible on the video (burn-in for 微信视频号 / 抖音 / WeChat — players that won't honor embedded subtitle tracks).
- User wants a togglable subtitle track (soft-mux) for QuickTime / VLC / IINA / mobile players that support
mov_text. - Final composite after
/wjs-dubbing-video: burn target-language subs + mix dub over original-as-bed in one encode.
When NOT to use
- No SRT yet → run
/wjs-transcribing-audiothen/wjs-translating-subtitlesfirst. - HTML/CSS captions (kinetic, per-word highlights, custom fonts) on a clip composed in HyperFrames → use
/wjs-overlaying-videoinstead. Don't mix libass burn-in with HyperFrames captions on the same output. - The "subtitles" are actually motion graphics (animated callouts, lower-thirds with logos, kinetic typography) → that's
/wjs-overlaying-video, not this skill.
The 3 modes of render.py
scripts/render.py auto-detects mode from flags:
- Subtitles only —
--video + --srt→ re-encodes video with burned subs, original audio passes through. - Dub only —
--video + --dub→ keeps original video stream; replaces or mixes the audio track. - Full localized cut —
--video + --srt + --dub→ burns subs AND mixes dub. By default keeps original audio at low volume as a "bed" under the dub (set--bed-volume 0or--no-original-audioto drop it).
Burn-in requires an ffmpeg built with libass. The script auto-downloads a static libass-enabled build from evermeet.cx into /tmp/ff_bin/ on first use if needed.
Soft-mux (togglable subtitle track)
Player apps can show/hide. Works with any ffmpeg build — does not need libass:
ffmpeg -i input.mp4 -i input.zh-CN.srt \
-map 0:v -map 0:a -map 1:0 \
-c:v copy -c:a copy -c:s mov_text \
-metadata:s:s:0 language=zho -metadata:s:s:0 title="中文" \
output.mp4
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 210 lines · 153 tokens per session scan A c6c4bec70dd6
wjs-burning-subtitles is a skill published in the GitHub repository jianshuo/claude-skills (129 stars, last pushed 23d ago), licensed MIT. It adds 153 tokens to every session and 3,297 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.