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 manishiitg/coding-agent-loop --skill video-editinggit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/video-editing)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/video-editing"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/video-editing/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/manishiitg/coding-agent-loop/video-editing"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/video-editing.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 | $0.00093 | $0.06104 |
| Opus 5.5 | $0.00037 | $0.02442 |
| Sonnet 5.5 | $0.00019 | $0.01221 |
| Haiku 4.5 | $0.00009 | $0.00610 |
Grade A, and why
video-editing 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 1mo 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit and assemble video
Keep the edit reproducible. Prefer scripts and manifests over one-off manual commands.
Own the HyperFrames runtime
When the approved production plan selects HyperFrames, install and run the current CLI through npx --yes hyperframes@latest. Use that full prefix for every HyperFrames command; do not depend on a global hyperframes binary and do not ask the user to install it. The first invocation downloads the latest published package automatically and later invocations reuse npm's cache.
Before authoring or rendering, verify the managed runtime:
npx --yes hyperframes@latest doctor --json
doctor --json always exits zero. Inspect its checks rather than using the top-level .ok as a universal render gate: current releases set .ok: false when optional transcription, local TTS, or local music fallbacks are absent. For ordinary local rendering, require Version, Node.js, FFmpeg, FFprobe, and Chrome; require Docker only for render --docker, and require optional media helpers only when the approved plan actually uses them. If npm cannot retrieve the package or a capability required by the selected operation is missing, record the exact failure instead of silently switching render runtimes. Never install HyperFrames globally and never change an approved render runtime merely because the global command is absent.
Normalize source media
- Inspect every input with
ffprobebefore editing. - Match the requested canvas without stretching. Scale to fit or fill intentionally, then pad or crop with the subject kept in the safe area.
- Normalize assembled segments to a common frame rate, pixel format, resolution, audio sample rate, and channel layout before concatenation.
- Use H.264 with
yuv420pand AAC for broadly playable MP4 exports unless the request requires another format. - CRF around 23 is a reasonable default for intermediate/working renders; tighten to roughly 18-20 for the final deliverable export (matches the re-encode fallback in "Stitching at true long-form scale" below).
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.
- 1mo ago Changed · -7 lines 4fa95785a0e4
- 1mo ago First seen · 456 lines · 93 tokens per session scan A 7af1c69cfb84
video-editing is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 25d ago), licensed MIT. It adds 93 tokens to every session and 6,104 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 2026-08-30.
Other skills, from other repositories
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
craft-studio
Router for the ArtCraft craft apps (PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft, DesignCraft, FigCraft, WordCraft, SoundCraft, DeckCraft, CADCraft, GridCraft) driven headless via pi-craft. Use to choose which app fits a job and run the discover-execute-save-verify loop - "which craft app…
craft-video-post
Footage/Veo clips to a finished mp4 with ArtCraft apps - FilmCraft assembly and alpha overlays, SRT captions, SoundCraft mix, h264+aac delivery; verified and resumable. Use for "edit these clips into a finished video with captions and music", "add a lower third and subtitles to my footage", "post-produce this…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…