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 agentmods add skills/opensolon/soloncode/solon-development-skillnpx skills add opensolon/soloncode --skill solon-development-skillgit clone --depth 1 https://github.com/opensolon/soloncodeWhat 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 | $0.00091 | $0.02396 |
| Opus 5 | $0.00046 | $0.01198 |
| Sonnet 5 | $0.00018 | $0.00479 |
| Haiku 4.5 | $0.00009 | $0.00240 |
Grade A, and why
solon-development-skill 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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solon Development Skill
为使用 Solon 框架 构建 Java 应用提供专家级指导。Solon 是独立的全场景 Java 企业应用框架 — 与 Spring 不兼容,拥有自研架构、注解体系与生态。
官网: https://solon.noear.org
GitHub: https://github.com/opensolon/solon
License: Apache 2.0
JDK: Java 8 ~ 26,GraalVM Native Image
目标版本: 4.0.3(升级时全局替换此标记 + 复核 AI/Nami 变更段)
Critical Rules
- Solon 不是 Spring。 禁止混用 Spring 注解(
@Autowired、@SpringBootApplication、@RestController、@RequestMapping、@Service、@Repository、@Value、@ComponentScan等)。 - 禁止 Spring 依赖。 不要引入
spring-boot-starter-*、spring-*。Solon 坐标 groupId 为org.noear。 - 配置文件是
app.yml(或app.properties),不是application.yml。 - 入口是
Solon.start(App.class, args),不是SpringApplication.run()。 - 组件注解用
@Component,不要用@Service/@Repository。 - 示例默认目标版本 4.0.3(除非用户指定其它版本)。
- Parent POM 为
solon-parent(groupId=org.noear)。 - 中文支持。 用户使用中文时,回复与代码注释使用中文。
- 不确定的 API 不要臆造。 优先查本 skill 的 reference;仍不确定时查官网/源码,禁止用 Spring 习惯补全。
执行流程
- 判定场景 → 只
read下表中对应的 1~2 个 reference(禁止一次加载全部)。 - 生成代码前核对 Critical Rules(尤其:
app.yml、@Component、@Inject、无 Spring 依赖)。 - 数据访问优先读
references/data_access.md。 - AI 场景分流:
- Chat/Tool/MCP/基础 RAG →
references/ai_chat_rag_mcp.md - Loader/向量库/搜索插件表 →
references/ai_rag_plugins.md - Agent/Talent/Loop →
references/ai_agent.md - HarnessEngine/工具权限 →
references/ai_harness.md - AI UI/ACP/A2A →
references/ai_protocol_ui.md
- Chat/Tool/MCP/基础 RAG →
- Cloud 分流:Config/Discovery/Event/Job →
references/cloud_core.md;File/Breaker/Gateway/Trace/Metric/Id/Lock →references/cloud_ops.md。 - Remoting 分流:Nami RPC/HttpClient →
references/remoting.md;过滤器/发现/LB →references/remoting_filter_lb.md;Socket.D →references/socketd.md。 - Flow 分流:YAML/Graph/节点 →
references/flow_orchestration.md;中断恢复/Workflow/拦截器 →references/flow_workflow.md。 - Security 分流:Auth/CORS/Vault →
references/security.md;参数校验 →references/validation.md。 - 从 Spring 迁移 → 使用
spring-to-solon-skill,本 skill 仅保留精简对照。 - 用户中文提问 → 中文回复与注释;默认版本 4.0.3。
- API 不确定时查 reference 或源码;禁止用 Spring 习惯或臆造坐标补全(例如不存在
solon-ai-rag/solon-ai-a2a)。
What ships with it
30 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.
- assets/minimal-web/App.java 224 B
- assets/minimal-web/app.yml 41 B
- assets/minimal-web/HelloController.java 411 B
- assets/minimal-web/pom.xml 968 B
- assets/minimal-web/README.md 467 B
- references/ai_agent.md 15 KB
- references/ai_chat_rag_mcp.md 8.4 KB
- references/ai_harness.md 15 KB
- references/ai_protocol_ui.md 4.5 KB
- references/ai_rag_plugins.md 2.3 KB
- references/api_reference.md 7.4 KB
- references/cloud_core.md 6.4 KB
- references/cloud_ops.md 8.2 KB
- references/common_patterns.md 4.2 KB
- references/core_concepts.md 11 KB
- references/data_access.md 8.9 KB
- references/flow_orchestration.md 6.1 KB
- references/flow_workflow.md 3.6 KB
- references/i18n.md 2.4 KB
- references/logging.md 3.3 KB
- references/modules_reference.md 6.7 KB
- references/plugin_spi.md 8.9 KB
- references/quick_start.md 5.7 KB
- references/remoting_filter_lb.md 4.8 KB
- references/remoting.md 13 KB
- references/security.md 7.0 KB
- references/socketd.md 6.1 KB
- references/testing.md 5.8 KB
- references/validation.md 4.9 KB
- references/web_sse_reactive.md 4.4 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.
- 2d ago First seen · 105 lines · 91 tokens per session scan A ebc1fa037778
solon-development-skill is a skill published in the GitHub repository opensolon/soloncode (185 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 2,396 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
philosophy-refinement
Use only when the user explicitly asks to change, review, or persist reusable development philosophy.
grill-me
Pressure-test a concrete decision, design, or plan only when the user asks to examine assumptions, alternatives, risks, or trade-offs.
deep-interview
Use only for an ambiguous product request; ask one plain-language question before proposing a brief.
programming
Use for a clear scoped implementation request; inspect local conventions and verify only the requested change.
implementation
Use after an approved, tested delivery boundary to implement it with focused verification.
plan
Use after product and technical inputs are concrete enough to choose a bounded delivery plan.