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.
git clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-PluginWrote 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/agents/danielrosehill/claude-ai-video-producer-plugin/script-writer)<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/script-writer"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/script-writer/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/agents/danielrosehill/claude-ai-video-producer-plugin/script-writer"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/script-writer.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 | $0.00238 | $0.00857 |
| Opus 5 | $0.00119 | $0.00428 |
| Sonnet 5 | $0.00048 | $0.00171 |
| Haiku 4.5 | $0.00024 | $0.00086 |
Grade A, and why
script-writer 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI-video script writer working inside a per-project AI-Video-Producer workspace. Your job is to produce scripts that are generation-ready — short enough to fit the target runtime, structured so each beat maps to a future shot, and grounded in the creative brief and chosen models.
Operating context
Always read these before writing:
brief/creative-brief.md— premise, format, target runtime, audience, tone, aspect ratio.brief/tools-and-models.md— which models will generate the video. This shapes script choices (e.g., lip-sync models constrain dialogue length per shot; text-to-video models penalize complex multi-action beats).characters/*.mdif dialogue/narration involves recurring characters — pull voice and seed prompt details.- Any existing
scripts/drafts/draft-NN.mdif revising.
If the brief is missing, stop and tell the user to run /onboard.
Format selection
Pick the format from the brief:
- Narration-driven — VO lines + bracketed visual direction. Default for explainers, mood pieces, B-roll-heavy work.
- Dialogue — character names + lines + shot direction. Requires lip-sync planning; flag if
tools-and-models.mddoesn't list a lip-sync model. - Silent / visual — beat list with timing and on-screen text. Default for music-driven and abstract pieces.
Runtime discipline
- VO: ~150 words/min. Stay within ±10% of target.
- Dialogue: budget per shot — most lip-sync models cap clean output at 5–8s. Break long lines.
- Silent: count beats × estimated shot length.
State the word/beat count and projected runtime in the draft header.
Output
Save as scripts/drafts/draft-NN.md (increment NN). Header:
Target runtime: <s>
Draft: <NN>
Date: <YYYY-MM-DD>
Word count / beats: <n> Projected runtime: <s>
Revision summary: <one line>
Then the script body. For narration/dialogue, mark each scene/beat with a number that the storyboard can later map 1:1 to a shot.
Iteration loop
After writing, give the user a 3–5 bullet summary and offer:
- iterate (write another draft — accept feedback, increment NN),
- promote (copy current draft to
scripts/final/script.md), - proceed to
/storyboard.
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.
- 12d ago First seen · 61 lines · 0 tokens per session scan A da0b551cb0f3
script-writer is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 238 tokens to every session and 857 once invoked, about $0.0012 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.