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 HashLips/agent-skills --skill story-architectgit clone --depth 1 https://github.com/HashLips/agent-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/skills/hashlips/agent-skills/story-architect)<a href="https://agentmods.dev/skills/hashlips/agent-skills/story-architect"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/story-architect/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/hashlips/agent-skills/story-architect"><img src="https://agentmods.dev/badge/skills/hashlips/agent-skills/story-architect.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 | $0.00054 | $0.01107 |
| Opus 5.5 | $0.00022 | $0.00443 |
| Sonnet 5.5 | $0.00011 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
story-architect 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 14d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Architect
Summary
- Turn each idea into one markdown file per concept.
- Classify, name, and place the file from the schema and category guide.
- Keep established canon. Fill only missing metadata when new canon arrives.
- Read this world's
AGENTS.mdbefore writing. If it is silent, use these defaults and continue. - Store standing preferences in that repo's
agent/folder.
Core Workflow
When the creator describes a world idea:
- Read root
AGENTS.mdand theagent/files it lists. If they are absent, use skill defaults. - Understand what the idea represents.
- Run a canon check against related entries. If
agent/canon-safety.mdexists, follow it. - Classify the concept with the built-in categories, then any category registered in
agent/categories.md. - Decide whether one file or several files are needed.
- Ask one minimal question only when classification or a required field is unclear.
- Generate the file or files from the schema and templates. Set
time_eraandtime_spanon every entry. Reuse an era label the repo already uses when one fits. - Enrich existing files when new canon fills missing metadata.
- When the creator asks to remember a way of working, write it under
agent/and index it fromAGENTS.md.
World-kit behavior: references/world-kit.md.
Non-Negotiable Rules
Scope Rule
Write lore and house rules into the world repository. Register a new category only when the creator wants that kind of entry. Take facts, era lists, and external IDs from the creator or from existing entries. Keep this world's preferences out of this skill.
World Kit Rule
Recorded preferences win over skill defaults. A missing preference does not block the task. Standing preferences are written into the repo, not left in chat. See references/world-kit.md.
Classification Rule
Infer the category when the creator does not name one. Use references/categories.md, then categories registered for this world.
What ships with it
7 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.
- 14d ago Changed · +12 lines · -20 tokens per session cf6fe098a111
- 1mo ago First seen · 86 lines · 74 tokens per session scan A f8de1bacf527
story-architect is a skill published in the GitHub repository HashLips/agent-skills (28 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 1,107 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.