agentmods.dev

sf-audit

sf-audit is a skill for Claude Code from maddexritter-rgb/vibe-editing. It costs 173 tokens per session (2,246 once invoked), scanned A, original, MIT.

A final quality checklist for vertical short videos, covering subtitles, audio, and picture. It automates many checks and flags others for a person to review.

In plain words
What is it for?
Use it to review finished MP4 or MOV clips, subtitle files, spelling, gaps, letter case, caption placement, audio levels, and video presentation.
Why use it?
It catches common delivery problems before a clip is sent for approval or publishing.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vibe-editing plugin — 18 skills shipped together

not rated 7repo +1 2mo ago A scan 173 tokens original MIT

Good fit Use it to review finished MP4 or MOV clips, subtitle files, spelling, gaps, letter case, caption placement, audio levels, and video presentation.

Compare 6 skills from other repositories ↓
View source ↗ maddexritter-rgb/vibe-editing
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add maddexritter-rgb/vibe-editing
Claude Code
/plugin install vibe-editing

Made for: Claude Code.

Or install vibe-editing, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for sf-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/sf-audit/github.svg)](https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/sf-audit)
Your own site
<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/sf-audit"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/sf-audit/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.

agentmods 80×15 button for sf-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/sf-audit"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/sf-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00173 $0.02246
Opus 5 $0.00086 $0.01123
Sonnet 5 $0.00035 $0.00449
Haiku 4.5 $0.00017 $0.00225

Measured 11d ago against content hash 19eae8c00304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sf-audit 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/vibe-editing/skills/sf-audit/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SF SF V1 Audit

The final-review checklist every short-form edit ships against. Based on the Team Speaker V1 MVP Standards (the studio). 16 checks (updated 2026-05-04 from 13 per the reference editor feedback), grouped into Subtitles / Audio / Video. Automates ~12 of them fully, flags the rest for a manual eye.

Read references/sf-standards.md for the full verbatim checklist with exceptions.

When to run

Before:

  • Uploading any finished short to your review tool for Brand review
  • Sending a .mp4 zip to Brand for posting
  • Marking a clip as "done" in the internal tracker

Integration:

  • shortform, qa-clipper, caption-clips, caption-burner, hook-overlay → all call this skill as the final step before declaring the clip ready
  • Can also run standalone on any .mp4 (plus optional .ass/.srt subtitle file)

Inputs

  1. Clip path — .mp4 (or .mov) at 9:16 (1080x1920 canonical)
  2. Subtitle file (optional but recommended) — .ass or .srt. If subtitles are burnt-in, skip and the spelling/gap/case/placement checks degrade to flag-for-manual.
  3. Speaker map (optional, for qa-clipper format) — JSON mapping time ranges to speaker (Speaker vs Guest), used by check #6 subtitle-color
  4. Platform — instagram (default) / tiktok / youtube-shorts — sets the UI safezone numbers

The 16 checks

Subtitles (7)

  1. Spelling / missing / double words — spellcheck non-proper-noun tokens; flag anything suspicious
  2. No blank gaps between subtitles (except >1s intentional pauses) — flag any visible gap >50ms; >30% of joints with gaps = fail
  3. NEW — Lower-half placement (not covering face) — anchor must be in lower half (y > height/2). Face overlap requires manual eye for now
  4. NEW — Subtitle timing matches dialogue (1-3 frame tolerance) — silencedetect maps speech regions; flag any cue displayed >50% during silence
  5. All words lowercased by default (proper nouns + "I/I'm/I'll" exempt) — regex + proper-noun whitelist
  6. Speaker vs Guest color differentiation — parse .ass styles; verify distinct colors
  7. All subtitles within UI safezone — IG 9:16 = top 13% / bottom 18% / sides 5% are UI-danger zones

Read the full file on GitHub · 145 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 11d ago First seen · 145 lines · 173 tokens per session scan A 19eae8c00304

Subscribe to this mod's changes

sf-audit is a skill published in the GitHub repository maddexritter-rgb/vibe-editing (7 stars, last pushed 2mo ago), licensed MIT. It adds 173 tokens to every session and 2,246 once invoked, about $0.0009 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 2026-08-31.

Creative and media
Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens