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 ChaosRealmsAI/NextFrame --skill clipsgit clone --depth 1 https://github.com/ChaosRealmsAI/NextFrameWrote 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/chaosrealmsai/nextframe/clips)<a href="https://agentmods.dev/skills/chaosrealmsai/nextframe/clips"><img src="https://agentmods.dev/badge/skills/chaosrealmsai/nextframe/clips.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00629 |
| Opus 5 | $0.00010 | $0.00315 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
clips 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 7d 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
clips · 视频剪辑(必跑完 6 步 · 不允许中途 stop)
NextFrame 完整 clips pipeline。6 步全跑 · 每步 Bash 一次 tool · 一直走到 karaoke HTML。
🔴 硬约束(违反 = 任务失败)
- ❌ 不允许中途 FINAL 停 · translate 和 karaoke 必须跑完
- ❌ 不允许在 plan 步输出完 plan.json 就停
- ❌ 不允许说"现在我需要翻译..." 然后不调 tool
- ✅ 每步调完 tool 立刻下一步
- ✅ 只有 karaoke 产出 index.html 后才能 FINAL
推进状态机(6 步 · 严格顺序)
Bash("nf-guide clips download")→ 调nf-source download· 产 source.mp4Bash("nf-guide clips transcribe")→ 调whisperx --model base.en(小模型 · 避免 1GB 下载)· 产 sentences.json + words.jsonBash("nf-guide clips plan")→ 你挑 1 个亮点写 plan.json(只挑 1 个 · 省 translate 工作量)Bash("nf-guide clips cut")→ ffmpeg 切 · 产 clip_01.mp4 + cut_report.jsonBash("nf-guide clips translate")→ 翻译(一次 Bash heredoc 写完整个 translations.zh.json · 不要逐句译)· 产 clip_01.translations.zh.jsonBash("nf-guide clips karaoke")→ 产 index.html(终点)
终点验收
ls <episode>/clips/ 必须有:
- clip_01.mp4
- cut_report.json
- clip_01.translations.zh.json
- index.html(karaoke · 字级同步)
反例(上次 agent 踩的坑)
❌ 错:"现在我需要翻译这 4 个英文句子..."(输出纯文本后停)
✅ 对:直接 Bash("cat > <path>/clip_01.translations.zh.json <<EOF ... EOF") 一次写完
视频选择(agent 自主)
用户让你自主选一个短视频(< 60s · 新鲜 · 不要 me-at-the-zoo)· 用 yt-dlp 下。建议挑:TED 短演讲 / 新闻片段 / 搞笑短剧 / 科技演示。
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.
- 7d ago First seen · 48 lines · 20 tokens per session scan A 98d2e4e82bb6
clips is a skill published in the GitHub repository ChaosRealmsAI/NextFrame (24 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 629 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
stage-compose
Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
stage-consistency
Multi-shot narrative & character consistency — a character bible with a locked front-portrait anchor, view-matched reference selection, recent-frame carry-forward, Cameo (a user photo as the lead), and global planning for long scripts/novels. Trigger on top of the generation line when the SAME character must look the…