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 WhiteTowerAI/cut-as-code --skill video-add-b-rollgit clone --depth 1 https://github.com/WhiteTowerAI/cut-as-codeWrote 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/whitetowerai/cut-as-code/video-add-b-roll)<a href="https://agentmods.dev/skills/whitetowerai/cut-as-code/video-add-b-roll"><img src="https://agentmods.dev/badge/skills/whitetowerai/cut-as-code/video-add-b-roll/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/whitetowerai/cut-as-code/video-add-b-roll"><img src="https://agentmods.dev/badge/skills/whitetowerai/cut-as-code/video-add-b-roll.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Privilege Escalation · line 43 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 401 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 509 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00034 | $0.09306 |
| Opus 5 | $0.00017 | $0.04653 |
| Sonnet 5 | $0.00007 | $0.01861 |
| Haiku 4.5 | $0.00003 | $0.00931 |
Grade A, and why
video-add-b-roll 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.
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 — 649 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Add B-Roll
Add a small number of evidence-backed visual cutaways to an understood canonical Project Protocol sequence. Read broll-rules.md before planning or acquiring any media. Use example-broll-plan.json as the plan-shape reference.
Non-Negotiable Contract
Follow every editorial, provenance, still, review, recovery, and delivery rule in broll-rules.md. Operationally:
- Use the provided scripts for acquisition, validation, normalization, receipt application, and verification. Never use a raw download path or substitute another stock source.
- Never fabricate human authority. Agent review requires explicit delegation and a truthful Agent receipt.
- Missing, weak, or downloader-rejected media becomes
skipped; never use random or still fallback media.
Requirements And Inputs
Require Python, ffmpeg, ffprobe, and Pillow. For Pexels, first use PEXELS_API_KEY from
the environment, then look for it in skills/video-add-b-roll/.env. If both are missing or
blank, stop and ask the user to add PEXELS_API_KEY=<key> to that file, then retry after they
confirm. Ask them to provide the key through the local .env file, never through chat. Never
place or print it in a command argument, plan, URL, log, review artifact, or response.
/video-understand is a prerequisite. Run it first so B-roll use the validated
word-level transcript and canonical timeline.
Before starting, verify that it is installed. If it is not, warn the user that
this prerequisite is missing and stop before processing media.
Run from the repository root and resolve the separate project root:
$RepoRoot = (Resolve-Path '.').Path
$ProjectRoot = (Resolve-Path 'path/to/video-project').Path
$BrollEnv = Join-Path $RepoRoot 'skills/video-add-b-roll/.env'
if ([string]::IsNullOrWhiteSpace($env:PEXELS_API_KEY) -and (Test-Path -LiteralPath $BrollEnv)) {
$PexelsKeyLine = Get-Content -LiteralPath $BrollEnv | Where-Object { $_ -match '^\s*PEXELS_API_KEY\s*=' } | Select-Object -Last 1
if ($PexelsKeyLine) { $env:PEXELS_API_KEY = ($PexelsKeyLine -split '=', 2)[1].Trim().Trim('"').Trim("'") }
}
$BrollScripts = Join-Path $RepoRoot 'skills/video-add-b-roll/scripts'
$ProjectLib = Join-Path $RepoRoot 'skills/video-understand/scripts'
$ReviewVideo = & python -c "import sys; from pathlib import Path; sys.path.insert(0,sys.argv[2]); import projectlib; root=Path(sys.argv[1]); project=projectlib.load_json(root/'work/project.json'); assert project.get('render',{}).get('status') == 'verified', 'current upstream delivery is not verified'; path=projectlib.resolve_project_path(root,project['render']['output']); assert path.is_file(), 'current upstream delivery is missing'; print(path)" $ProjectRoot $ProjectLib
if ($LASTEXITCODE -ne 0) { throw 'Complete the active upstream delivery before B-roll review.' }
$ReviewVideo = (Resolve-Path -LiteralPath $ReviewVideo).Path
What ships with it
13 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.
- assets/broll-review.html 50 KB
- examples/example-broll-plan.json 7.6 KB
- examples/example-candidate-ranking.json 6.6 KB
- reference/broll-rules.md 31 KB
- scripts/broll_plan.py 146 KB runs code
- scripts/build_review_page.py 24 KB runs code
- scripts/candidate_analysis.py 91 KB runs code
- scripts/check_broll.py 45 KB runs code
- scripts/normalize_broll.py 40 KB runs code
- scripts/pexels.py 18 KB runs code
- scripts/speaker_inset.py 99 KB runs code
- tests/test_broll.py 505 KB runs code
- tests/test_normalize_broll_frames.py 14 KB runs code
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.
- 9d ago First seen · 649 lines · 34 tokens per session scan A 0050a56a6ab7
video-add-b-roll is a skill published in the GitHub repository WhiteTowerAI/cut-as-code (11 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 9,306 once invoked, about $0.0002 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
smart-video-editor
A video-editing workflow that examines raw clips, selects usable moments, arranges them into a story, and renders a finished video with FFmpeg.
create_profile_style_skill
A workflow for turning a person's video-editing habits into a reusable editing skill file. It examines choices such as pacing, storytelling, audio, subtitles, colour, transitions, and recurring editing rules.
subtitle_imitation_skill
A video-writing workflow that rewrites a script to match the style of reference text supplied by the user. It uses the footage analysis and reference sample while keeping the script tied to what is actually shown.
premiere-pro-mcp
Install, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues.
ai_transition_editing_skill
A video-editing workflow that connects existing clips with AI-generated transitions. It can organize clips, choose background music, build a timeline, and render the finished video.
default_editing_workflow_skill
A general video-editing workflow for turning uploaded or found footage into a finished video. It covers loading clips, organizing a story, adding text, voiceover, music, and effects, then rendering the result.