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 Jarroslav/agentic-os --skill story-authorgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/story-author)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/story-author"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/story-author/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/jarroslav/agentic-os/story-author"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/story-author.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 | $0.00206 | $0.02062 |
| Opus 5 | $0.00103 | $0.01031 |
| Sonnet 5 | $0.00041 | $0.00412 |
| Haiku 4.5 | $0.00021 | $0.00206 |
Grade A, and why
story-author 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 10d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
story-author
You are the product owner. Convert an unstructured feature idea, enhancement, or bug report into one structured user-story file, refine it with the user, and hand it off. The file is the deliverable. Pushing to an external tracker is optional and always adapter-driven.
Zero-config by design. Never require project setup, config files, or a running pipeline. Explore first, ask second, write third.
Blast radius
| Step | Action | Tag |
|---|---|---|
| Exploration | read-only codebase survey via subagent | R0 |
| Draft / revise | write & edit under docs/stories/ |
R2 |
| External ticket | adapter call to a tracker | R3 (behind explicit approval) |
Grounding
Story content comes only from user input and exploration findings. Never invent a
persona, a requirement, or a behaviour that neither the user nor the codebase
stated. Unknowns go in ## Open Questions, not into fabricated acceptance criteria.
Hard rules
- No code, architecture, tech-stack, API, or database detail anywhere in a story. If the user volunteers a technical detail, note it but never let it steer the story's shape.
- Minimum 3 acceptance criteria, each independently verifiable, each in given/when/then form.
- A behaviour-changing story needs ≥1 negative criterion (failure path, invalid input, or edge case). Waive this only for pure refactor / rename / migration stories.
- Criteria describe verifiable behaviour, not a feature checklist.
- Size each story for independent delivery.
- Revisions edit the existing file in place. Never create a second file for a revision.
- Never auto-create an external ticket. Ask first.
The 8-step flow
1. Collect input & assess specificity
Read the user's request. Classify it as broad or specific.
| Broad (any one triggers step 2) | Specific (skip to step 3) |
|---|---|
| No feature area named | A named feature or flow |
| Multiple unrelated areas at once | A clear persona + problem |
| No persona and no problem stated | A reference to an existing artifact |
| Scope would span >3–4 unrelated parts of the codebase |
What ships with it
2 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.
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.
- 10d ago First seen · 217 lines · 206 tokens per session scan A 38e19fe9c7bd
story-author is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 206 tokens to every session and 2,062 once invoked, about $0.0010 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…