Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XziXmn/legado-hubnpx agentmods add skills/xzixmn/legado-hub/book-source-craftWrote 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/xzixmn/legado-hub/book-source-craft)<a href="https://agentmods.dev/skills/xzixmn/legado-hub/book-source-craft"><img src="https://agentmods.dev/badge/skills/xzixmn/legado-hub/book-source-craft/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/xzixmn/legado-hub/book-source-craft"><img src="https://agentmods.dev/badge/skills/xzixmn/legado-hub/book-source-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.00855 |
| Opus 5 | $0.00045 | $0.00428 |
| Sonnet 5 | $0.00018 | $0.00171 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
book-source-craft 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Source Craft
Use this skill to create or review LegadoHub Python source plugins and the thin Reading/Legado aggregate shell that exposes LegadoHub to the Reading app.
Core Principles
- Treat Reading/Legado as an output compatibility surface, not the internal source format.
- Work module by module: metadata, search, detail, toc, chapter, then smoke tests.
- Keep concurrency, timeout, proxy, cache, retry, and health scoring in LegadoHub core.
- Put only site-specific adaptation inside the plugin.
- Prefer evidence from live HTML, captured pages, failed traces, public source JSON, or saved samples over guessing selectors.
- Prefer existing source templates before writing one-off plugin logic.
- Keep aggregate source-side JS thin; put heavy logic in LegadoHub service APIs.
- Treat public source repositories as examples and pattern references, not blindly trusted runtime code.
Source Types
Choose the path before writing rules:
- Python source plugin: a LegadoHub-native plugin implementing search, detail, toc, and chapter.
- Template-based plugin: a plugin that inherits or configures a common repeated-site template.
- Special-site plugin: a plugin with custom token, signing, decryption, pagination, or anti-bot handling.
- Aggregate shell source: a single Reading/Legado source that calls LegadoHub APIs.
- Imported source review: inspect existing public source JSON or So Novel rules and summarize reusable patterns.
Required Workflow
- Identify target: website URL, captured page, existing source JSON, aggregate API, or public source repository.
- Check accessibility and encoding for live sites.
- Inspect reference examples and existing templates before creating plugin code.
- Draft the smallest useful plugin module.
- Run search/detail/toc/chapter smoke checks through LegadoHub tooling when available.
- Repair from concrete failure evidence instead of rewriting blindly.
- Deliver plugin files plus a short validation checklist.
What ships with it
9 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.
- agents/openai.yaml 205 B
- README.md 5.2 KB
- references/aggregate-source-pattern.md 2.7 KB
- references/legado-module-workflow.md 4.1 KB
- references/plugin-source-workflow.md 5.2 KB
- references/public-source-references.md 2.8 KB
- references/source-plugin-template.md 13 KB
- references/source-plugin-template.zh-CN.md 8.2 KB
- references/stage-2-plugin-production.md 1.9 KB
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.
- 12d ago First seen · 80 lines · 90 tokens per session scan A 6058826cadde
book-source-craft is a skill published in the GitHub repository XziXmn/legado-hub (64 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 855 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 2026-08-30.
Other skills, from other repositories
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
azure-messaging-webpubsubservice-py
Azure Web PubSub Service SDK for Python. Use for real-time messaging, WebSocket connections, and pub/sub patterns. Triggers: "azure-messaging-webpubsubservice", "WebPubSubServiceClient", "real-time", "WebSocket", "pub/sub".
azure-mgmt-botservice-py
Azure Bot Service Management SDK for Python. Use for creating, managing, and configuring Azure Bot Service resources. Triggers: "azure-mgmt-botservice", "AzureBotService", "bot management", "conversational AI", "bot channels".
backend
Python server code, APIs, async, strict typing.