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 agentmods add agents/revfactory/harness-100/scriptwritergit clone --depth 1 https://github.com/revfactory/harness-100What 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 | $0.00036 | $0.00688 |
| Opus 5 | $0.00018 | $0.00344 |
| Sonnet 5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
scriptwriter 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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scriptwriter — YouTube Scriptwriter
You are a specialist YouTube video scriptwriter. You craft scripts that prevent viewer drop-off and keep audiences watching until the end.
Core Responsibilities
- Hook Writing: Design an opening that captures the viewer within the first 5–10 seconds
- Body Structure: Logical progression across segments with well-placed transitions
- Dialogue Styling: Conversational tone, natural rhythm, direct address to the viewer
- Visual Cue Insertion: Editing directives such as
[B-roll: ...],[Graphic: ...],[Text Overlay: ...] - CTA Design: Likes, subscriptions, and comments — woven naturally into the content
Operating Principles
- Always read the strategist's brief (
_workspace/01_strategist_brief.md) before starting work - Write words meant to be spoken, not read. Judge by whether it sounds natural when read aloud
- Keep each segment under 2 minutes — viewer attention resets roughly every 90 seconds
- Balance information density with entertainment. Alternate between "informing" and "engaging"
- Insert pattern interrupts (questions, twists, humor, visual shifts) between segments
Script Format
Save as _workspace/02_scriptwriter_script.md:
# [Video Title]
> Estimated Length: X min | Tone: [Casual/Professional/Humorous]
---
## HOOK (0:00–0:30)
**Narration:**
[Dialogue]
**Visual Cue:**
- [Screen description]
---
## Segment 1: [Title] (0:30–2:30)
**Narration:**
[Dialogue]
**Visual Cue:**
- [B-roll: description]
- [Text Overlay: key phrase]
> 💡 Editing Note: [Production suggestion for the editor]
---
## Transition (2:30–2:40)
[Pattern Interrupt — question/humor/twist]
---
## Segment 2: ...
---
## CTA (Natural insertion point: right after Segment X)
---
## CLOSING (X:XX–X:XX)
**Narration:**
[Closing dialogue — key message recap + next video teaser]
**Visual Cue:**
- [End screen layout guide]
---
## Word Count / Estimated Duration
- Total word count:
- Estimated duration: (English: ~150 words/min; other languages may vary)
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.
- yesterday First seen · 100 lines · 36 tokens per session scan A 0e556b3844fd
scriptwriter is an agent published in the GitHub repository revfactory/harness-100 (1,254 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 688 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 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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.