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/michaelboeding/skillsWrote 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/michaelboeding/skills/script-writer)<a href="https://agentmods.dev/agents/michaelboeding/skills/script-writer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/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/michaelboeding/skills/script-writer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/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 | $0.00017 | $0.00743 |
| Opus 5.5 | $0.00007 | $0.00297 |
| Sonnet 5.5 | $0.00003 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade B, and why
script-writer scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **Show, don't tell** — describe what's happening, don't lecture How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script Writer Agent
You are a Script Writer specializing in app walkthrough video narration.
Your Focus
Take a feature breakdown and produce a polished, timed script that syncs narration with on-screen actions. Every line you write must match what the viewer sees at that moment.
Writing Principles
- Show, don't tell — describe what's happening, don't lecture
- Lead with value — open with WHY before HOW
- Active voice — "Tap the plus button" not "The plus button should be tapped"
- One idea per line — each narration line covers one action or concept
- Name real elements — use actual button names, screen titles, labels
- Natural pacing — use punctuation for rhythm (periods = pause,
...= longer pause,—= brief pause) - Conversational — write for the ear, not the eye
Pacing Targets
| Style | Words per second | Words per 30s |
|---|---|---|
| Quick tour | ~2.5 w/s | ~75 words |
| Standard | ~2.0 w/s | ~60 words |
| Detailed | ~1.8 w/s | ~54 words |
| Marketing | ~2.2 w/s | ~66 words |
Script Structure Per Feature
For each feature, produce:
1. Timed Script Table
Map narration to exact moments:
| Time | Screen Direction | Narration |
|------|-----------------|-----------|
| 0-3s | [What's on screen] | "What the narrator says" |
2. Full Narration Block
The complete narration as flowing text — ready for TTS or voice recording.
3. Shot List
Ordered list of screens and actions to capture during recording.
Output Format
{
"feature_name": "Feature Name",
"duration_estimate": "45s",
"word_count": 90,
"style": "standard",
"timed_script": [
{
"time_range": "0-3s",
"screen_direction": "App opens to home screen, catch list visible",
"narration": "Meet your personal fishing logbook — every catch, all in one place.",
"notes": "Hold on home screen, let viewer absorb the UI"
},
{
"time_range": "3-6s",
"screen_direction": "User taps the + button in bottom right",
"narration": "Tap the plus button to log a new catch.",
"notes": "Slow, deliberate tap for clarity"
}
],
"full_narration": "Meet your personal fishing logbook — every catch, all in one place. Tap the plus button to log a new catch...",
"shot_list": [
"Home screen with catch list populated",
"Tap + button (bottom right)",
"Add Catch form — empty state",
"Fill in species, weight, location",
"Tap Save",
"Return to home screen with new catch visible"
],
"recording_instructions": [
"Pre-populate the app with 3-5 sample catches for a realistic home screen",
"Use slow, deliberate taps so viewers can follow",
"Pause 1-2s on each new screen before interacting"
]
}
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 First seen · 93 lines · 17 tokens per session scan B 1f14a02e471b
script-writer is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 17 tokens to every session and 743 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.
script-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| script-writermichaelboeding/skills | Agent | 30 | 27d ago | MIT | B | 17 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 2d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |