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/3taste/timefold-java-skill/timefold-javanpx skills add 3Taste/timefold-java-skill --skill timefold-javagit clone --depth 1 https://github.com/3Taste/timefold-java-skillWhat 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 | $0.00102 | $0.02063 |
| Opus 5 | $0.00051 | $0.01032 |
| Sonnet 5 | $0.00020 | $0.00413 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
timefold-java 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Timefold Java Skill
核心定位：从业务需求 → Timefold 领域模型 + 约束 + 求解器配置的方法论 + 能力目录。
不是"场景查找表"。遇到任何新排程需求（教学排课、车辆路径、人员排班、半导体生产排程、项目调度 ...）都走同一套 6 步法。
触发条件
使用本 skill 当用户请求涉及：
- 任务 / 资源 / 时间的分配或排程（产线排程、车辆路径、人员排班、课表、会议室）
- 优化问题：在硬约束下最大化 / 最小化某目标
- 显式提到 Timefold / OptaPlanner / ConstraintProvider / @PlanningEntity
- 中文关键词：排程、排产、排班、调度、分配、规划、优化、约束
- "给 X 安排 Y"、"在时间 / 机台 / 人员约束下"、"最小化成本 / 最大化吞吐"
首要动作：走 6 步建模方法论
拿到需求先做 6 步抽象，不要直接写代码。详见 references/modeling-methodology.md。
- 识别规划实体：哪些对象"需要被安排"？（
@PlanningEntity） - 识别规划变量：实体的什么属性是解空间？单值 / 有序列表？（
@PlanningVariable/@PlanningListVariable） - 识别值域：变量取值是静态全局还是动态按实体过滤？（
@ValueRangeProvider位置） - 识别派生状态：哪些字段是算出来的？（
@InverseRelationShadowVariable/@PreviousElementShadowVariable/@ShadowVariable+@ShadowSources/@CascadingUpdateShadowVariable） - 分类约束：硬 / 中 / 软，每条归到 cookbook 的范式
- 选择求解器配置与集成：纯 JAR / Spring Boot / Quarkus + termination 策略
每一步对应的能力都在 references/capability-catalog.md。
输出物清单（每次需求都产出）
- 领域类骨架（Entity / Fact / Solution）
- 变量 / Shadow 选型表（字段 → 注解 + 理由）
- 硬/中/软约束分类表（每条 → 一行 ConstraintStream）
- 求解器配置建议（termination + 集成方式 + 是否 ProblemChange）
- 测试提示（每条约束对应的 ConstraintVerifier 测试）
能力索引（快速定位注解 / API）
完整细节见 references/capability-catalog.md。
| 建模需求 | Timefold 能力 | 能力目录章节 |
|---|---|---|
| 实体从值域选 1 个 | @PlanningVariable |
§1 |
| 实体排成有序列表（路径 / 工序链 / 装载） | @PlanningListVariable + 配套 shadow |
§2 |
| 反查列表载体 | @InverseRelationShadowVariable |
§3.1 |
| 列表中的前 / 后 / 索引 | @PreviousElementShadowVariable / @NextElementShadowVariable / @IndexShadowVariable |
§3.2 / §3.3 |
| 派生字段（到达时间、总成本） | @ShadowVariable(supplierName) + @ShadowSources |
§3.4 |
| 沿列表级联派生 | @CascadingUpdateShadowVariable |
§3.5 |
| 允许部分实体不分配 | allowsUnassigned=true / allowsUnassignedValues=true |
§4 |
| 冻结已确定的排程 | @PlanningPin / @PlanningPinToIndex |
§5 |
| 动态值域（按实体过滤） | 实体级 @ValueRangeProvider |
§6 |
| 选分数类型 | HardSoftScore / HardMediumSoftScore / BendableScore / *LongScore |
§7 |
| 约束逻辑 | ConstraintProvider + ConstraintStream DSL |
§8 |
| 运行时调权重 | ConstraintWeightOverrides |
§8.2 |
| 异步求解（Web 服务） | SolverManager |
§9.2 |
| 分数解释 | SolutionManager.analyze() |
§9.3 |
| 实时变更 | ProblemChange |
§10 |
| 大规模加速 | Nearby Selection | §11 |
| 区间聚类 / 间隙检测 | toConnectedRanges / toConnectedTemporalRanges |
§13 |
| 方案对比（Preview） | SolutionManager.diff() |
§14 |
| 自定义 Move（Preview） | Neighborhoods API | §15 |
| 新元启发式（Preview） | Diversified Late Acceptance | §16 |
What ships with it
14 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/skeleton/pom.xml 2.0 KB
- assets/skeleton/README.md 701 B
- assets/skeleton/src/main/java/com/example/App.java 1.3 KB
- assets/skeleton/src/main/java/com/example/domain/MyEntity.java 877 B
- assets/skeleton/src/main/java/com/example/domain/MySolution.java 1.2 KB
- assets/skeleton/src/main/java/com/example/domain/MyValue.java 408 B
- assets/skeleton/src/main/java/com/example/solver/MyConstraintProvider.java 1.1 KB
- assets/skeleton/src/test/java/com/example/solver/MyConstraintProviderTest.java 1.2 KB
- references/capability-catalog.md 18 KB
- references/constraint-cookbook.md 13 KB
- references/integration.md 8.5 KB
- references/modeling-methodology.md 16 KB
- references/solver-tuning.md 7.9 KB
- references/testing-patterns.md 6.8 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 · 126 lines · 102 tokens per session scan A 7c9eb16548b0
timefold-java is a skill published in the GitHub repository 3Taste/timefold-java-skill (6 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 102 tokens to every session and 2,063 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.