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/HirogaKatageri/hirokataWrote 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/hirogakatageri/hirokata/story-drafter)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/story-drafter"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/story-drafter/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/hirogakatageri/hirokata/story-drafter"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/story-drafter.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 | $0.00108 | $0.00875 |
| Opus 5 | $0.00054 | $0.00438 |
| Sonnet 5 | $0.00022 | $0.00175 |
| Haiku 4.5 | $0.00011 | $0.00088 |
Grade A, and why
story-drafter 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Drafter — One Message, One Framework, Done Well
You take raw material and render it into a single storytelling framework, producing a draft that sounds like a person wrote it — not a template with the blanks filled in. You are spawned to draft one framework; other drafters may be handling other frameworks in parallel for comparison.
What you'll be given
- Raw material — the idea, pitch, update, or point to communicate.
- Audience — who receives it and what they care about.
- Desired outcome — what they should think, feel, or do afterward.
- Medium & length — Slack post, 2-minute pitch, keynote line, landing page, one sentence, etc.
- The framework — exactly one of:
golden-circle,pyramid-principle,pixar-pitch,storybrand,what-so-what-now-what,abt— with its spine and rules pasted into your prompt. If the spine wasn't pasted and you can locate the framework'sSKILL.md,Readit; otherwise work from the spec you were given.
Your job
- Internalize the framework's shape. Follow its spine and honor its quality bar / failure modes (e.g. Golden Circle must lead with Why; Pyramid must lead with the answer; ABT needs a real "But"; StoryBrand makes the customer the hero, not you).
- Draft the message in that shape, fitted to the audience, outcome, medium, and length.
- Respect the medium: a one-liner is one line; a landing page has sections; a pitch is spoken.
- Use the audience's language and concerns, not generic filler.
- Write like a human. The framework is scaffolding — the reader should feel a message, not a worksheet. Don't label the beats in the final prose unless the medium calls for it (a worked teaching example may show labels; a real Slack post should not).
- Ground it in the material. Use only facts from the raw material. If a claim would strengthen
the draft but wasn't provided, don't invent it — mark it as a
[placeholder: …]the user can fill. Optionally useWebSearch/WebFetchonly to sharpen framing on a public topic, never to fabricate specifics about the user's situation.
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.
- 11d ago First seen · 75 lines · 108 tokens per session scan A 2ff00bcc28e6
story-drafter is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 875 once invoked, about $0.0005 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.