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 lujiafa/houtu-project-skills --skill houtu-dependenciesgit clone --depth 1 https://github.com/lujiafa/houtu-project-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/lujiafa/houtu-project-skills/houtu-dependencies)<a href="https://agentmods.dev/skills/lujiafa/houtu-project-skills/houtu-dependencies"><img src="https://agentmods.dev/badge/skills/lujiafa/houtu-project-skills/houtu-dependencies/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/lujiafa/houtu-project-skills/houtu-dependencies"><img src="https://agentmods.dev/badge/skills/lujiafa/houtu-project-skills/houtu-dependencies.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 | $0.00283 | $0.05473 |
| Opus 5 | $0.00142 | $0.02736 |
| Sonnet 5 | $0.00057 | $0.01095 |
| Haiku 4.5 | $0.00028 | $0.00547 |
Grade A, and why
houtu-dependencies 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Houtu Framework — AI Agent Coding Guide
houtu-dependencies is an enterprise-grade foundational framework for Spring Boot / Spring Cloud microservices that implements "Activate-on-import" via the Spring Boot Starter mechanism, allowing developers to focus entirely on business logic.
Repository: https://github.com/lujiafa/houtu-dependencies
Git Branches: 3.5.2, 3.5.1, 3.5.0, 2.7.3, 2.7.2, 2.7.1 (branch name = version)
Core Principles
- Activate-on-import — Capabilities are automatically enabled after adding a starter dependency; no @Enable annotations or manual configuration needed
- Annotation-driven — Control behavior through annotations (
@Lock,@CheckSession,@SecurityWatch...); do not hand-write interceptors/AOP - Framework-first — For capabilities already encapsulated by the framework, use the framework approach by default instead of native Spring; defer to user when they explicitly request the native approach
- Convention over configuration — Follow framework defaults; only override when customization is needed
- Version-aware — Package paths, API names, and configuration approaches differ across versions; the version must be confirmed before generating code
Code Generation Workflow (must be executed in order)
Step 1: Detect Version & Dependencies → Step 2: Identify Scenario → Step 3: Load Module Reference → Step 4: Generate Code → Step 5: Verify
Step 1 — Detect Version & Dependencies
The version must be determined before generating any code, and the BOM must be imported.
Read the project build file (pom.xml or build.gradle / build.gradle.kts) and determine in the following order:
1a. houtu already imported — The build file contains houtu-dependencies or spring-cloud-houtu:
- Read the version number directly to determine the version, proceed to Step 2
- Multi-module projects: The BOM is usually declared in the root
pom.xmlor rootbuild.gradleunderdependencyManagement; submodules inherit it and do not need to add it again
What ships with it
21 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.
- evals/evals.json 10 KB
- README-CN.md 2.0 KB
- README.md 2.1 KB
- references/module-access-log.md 4.0 KB
- references/module-actuator.md 7.0 KB
- references/module-cache-lock.md 4.7 KB
- references/module-cloud.md 7.2 KB
- references/module-concurrent.md 4.8 KB
- references/module-config-decrypt.md 2.6 KB
- references/module-data-security.md 4.9 KB
- references/module-security.md 11 KB
- references/module-swagger.md 2.7 KB
- references/module-utils.md 19 KB
- references/module-web.md 9.8 KB
- references/quick-start.md 5.7 KB
- references/v2.7.1.md 2.2 KB
- references/v2.7.2.md 2.2 KB
- references/v2.7.3.md 4.1 KB
- references/v3.5.0.md 1.5 KB
- references/v3.5.1.md 2.1 KB
- references/v3.5.2.md 4.5 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 · 351 lines · 283 tokens per session scan A df8f19bf5567
houtu-dependencies is a skill published in the GitHub repository lujiafa/houtu-project-skills (26 stars, last pushed 4mo ago), licensed MIT. It adds 283 tokens to every session and 5,473 once invoked, about $0.0014 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
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
okhp3-verse-lookup
Fetch or integrate scripture passages from Judaism, Christianity, or Islam through the ARE free anonymous providers. Use for verse lookup, API endpoint and reference-format questions, translation IDs, normalization, attribution, error handling, fallback routing, or denomination-aware scripture UI work. Covers Sefaria…
openapi-to-application-code
Generate a complete, production-ready application from an OpenAPI specification.
feature-workflow
Phased workflow for delivering a Drupal feature or non-trivial change: plan, implement, review, test, finalize. Use when building a new custom module, adding a route/form/plugin, changing entity structure or schema, or any task touching more than a couple of files. Do NOT use for typo fixes, CSS tweaks, or single-line…
ddd-best-practices
Domain-Driven Design guidance for modeling complex domains. Use when designing Bounded Contexts or Subdomains, discovering Aggregate boundaries from invariants and transactions, defining Aggregate Roots, designing Domain Events, typed domain failures, or repository contracts, choosing exception vs Result/Either/Option…