audit-script

audit-script is a skill for Claude Code from maddexritter-rgb/vibe-editing. It costs 118 tokens per session (1,545 once invoked), scanned A, original, MIT.

An editorial script checker that reads only a video's transcript and tests whether its words make sense to someone seeing the clip without prior context.

In plain words
What is it for?
Use it to review rendered clips for viewer comprehension, context before important points, a clear single storyline, brand-safety issues, and compliance with editorial rules.
Why use it?
It catches unclear references, unexplained terms, weak openings, broken logical flow, and other script problems that may confuse a new viewer.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

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

Good fit Use it to review rendered clips for viewer comprehension, context before important points, a clear single storyline, brand-safety issues, and compliance with editorial rules.

Compare 6 skills from other repositories ↓
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 audit-script

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/audit-script"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/audit-script.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,545 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 $0.00118 $0.01545
Opus 5 $0.00059 $0.00772
Sonnet 5 $0.00024 $0.00309
Haiku 4.5 $0.00012 $0.00154

Measured 9d ago against content hash c2e89a607d47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-script 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check.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/audit-script/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

audit-script — editorial-only quality gate

Fresh-context agent. Receives ONLY the transcript text of the rendered clip. No video, no audio, no editing context. Tests whether the WORDS make sense to a cold viewer who just opened this video.

How to run

python3 ${CLAUDE_PLUGIN_ROOT}/skills/audit-script/scripts/check.py \
    --clip 20_DELIVER/v1/clip.mp4 \
    --out 10_WORK/audit_script.json

The script transcribes the clip independently (Groq), then runs all editorial checks on the text. It does NOT read any prior transcript or mining results.

What it checks

1. COLD VIEWER TEST — does every line make sense with zero context?

  • Read the transcript as if you just opened this video with no prior knowledge
  • For each line, ask: "Does this make complete sense given ONLY the lines before it?"
  • Flag: dangling references ("that focus", "what he said", "the same thing", "her ex") where the referent was never stated in this clip
  • Flag: jargon or terms used without definition ("one avatar", "grand slam offer", "the funnel") that a cold viewer wouldn't understand
  • Flag: mid-conversation continuations ("...and that's why", "so basically", "the point is") that assume the viewer heard something they didn't
  • FAIL if any line requires context the clip doesn't provide

2. CONTEXT BEFORE PAYOFF — is the setup present?

  • If this is a Q&A/commentary clip: does the QUESTION appear before the ANSWER?
  • If this is a story clip: is there a setup before the punchline?
  • If this is advice: is the PROBLEM stated before the SOLUTION?
  • The viewer should understand WHY the speaker is saying what they're saying
  • FAIL if payoff arrives without setup

3. ONE-ARC RULE — one topic, one story, one payoff?

  • The clip should cover ONE thing. Not two half-stories stitched together.
  • Flag: topic changes mid-clip ("...anyway, on a different note", or an abrupt shift from pricing to hiring to marketing)
  • Flag: two separate Q&A pairs merged into one clip
  • FAIL if the clip contains more than one distinct topic/arc

Read the full file on GitHub · 136 lines

Files

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.

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. 9d ago First seen · 136 lines · 118 tokens per session scan A c2e89a607d47

Subscribe to this mod's changes

audit-script is a skill published in the GitHub repository maddexritter-rgb/vibe-editing (7 stars, last pushed 2mo ago), licensed MIT. It adds 118 tokens to every session and 1,545 once invoked, about $0.0006 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.

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

diagnostic-stem-delivery

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

HKUDS/OpenSpace · 23 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