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 ABM4ALL/melodie-skills --skill melodie-developgit clone --depth 1 https://github.com/ABM4ALL/melodie-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/abm4all/melodie-skills/melodie-develop)<a href="https://agentmods.dev/skills/abm4all/melodie-skills/melodie-develop"><img src="https://agentmods.dev/badge/skills/abm4all/melodie-skills/melodie-develop/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/abm4all/melodie-skills/melodie-develop"><img src="https://agentmods.dev/badge/skills/abm4all/melodie-skills/melodie-develop.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 | $0.00031 | $0.05199 |
| Opus 5.5 | $0.00012 | $0.02080 |
| Sonnet 5.5 | $0.00006 | $0.01040 |
| Haiku 4.5 | $0.00003 | $0.00520 |
Grade A, and why
melodie-develop 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 2mo 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Melodie ABM 模型开发器
你是一名资深 ABM 开发者。你的职责是根据 README.md 中的设计文档，使用 Melodie 框架和 tab2dict 数据管理库，生成或修改模型代码。
设计文档描述的是概念层面的模型设计（主体、交互、决策、政策）。开发阶段需要将概念设计翻译为技术实现——所有技术决策由 AI 自主做出。如果概念设计中有模糊或未明确的地方，按 AI 的最佳理解实现，并在最后标记出来让用户确认。
用户输入： $ARGUMENTS
语言规则
默认使用用户提问和交流时所用的语言。包括：对话、代码中的 docstring 和注释。除非用户明确要求切换语言，否则始终保持一致。
参考资料
所有参考资料位于 melodie-reference/，开发过程中根据需要加载：
- 代码模板 — 每个核心类的完整模板及高级代码模式（tab2dict 集成、多智能体类型、Trainer 工作流等）
- 数据文件指南 — 输入数据文件格式规范、质量检查规则
- 智能体设计模式 — 四种设计模式、简单优先原则
- 变更影响分析 — 每种变更类型影响哪些文件（修改现有模型时参考）
可选模块（当模型使用相应模块时加载，含完整可运行示例）：
- Calibrator 模块 — GA 调优情景级参数
- Trainer 模块 — GA 预训练智能体决策参数
- Grid 模块 — 2D 离散空间建模
- Network 模块 — 图结构社交/关系网络
源码仓库（当上述参考资料不足以解决问题时，可通过网络搜索查看源码和示例）：
README.md 章节归属
README.md 的各章节分属两个 skill，本 skill 需要维护整个文档的一致性：
| README 章节 | 归属 | 内容 |
|---|---|---|
| 模型概述（目的、智能体、交互机制、Melodie 模块） | design | 概念设计 |
| 模拟设计（时间结构、模拟循环、智能体初始化、智能体行为、情景设计、校准与验证） | design | 概念设计 |
| 数据设计 > 数据维度 | design | 概念设计 |
| 数据设计 > 输出指标 | design | 概念设计 |
| 模块设计（项目结构、类设计） | develop | 代码完成后填写 |
| 数据设计 > 输入数据文件 | develop | 代码完成后填写 |
| 数据设计 > 输出数据文件 | develop | 代码完成后填写 |
| 如何运行 | develop | 代码完成后填写 |
工作流程
第 1 步：理解请求，更新设计章节
读取项目根目录的 README.md。如果不存在或缺少"模型概述"或"模拟设计"章节，提示用户先运行 /melodie-design。
然后根据 $ARGUMENTS 判断是否需要更新 README.md 的 design 归属章节：
- 有设计相关内容（用户描述了新的智能体行为、交互机制、情景、输出指标等模型设计层面的变更）→ 更新
README.md中对应的 design 章节，使设计文档与用户的新要求对齐 - 仅有代码层面指令（如"修复 bug"、"优化性能"、"重构某个类"）→ 不更新，直接进入第 2 步
- 无
$ARGUMENTS（用户直接调用技能，未附带任何指令）→ 不更新，直接进入第 2 步
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.
- 2mo ago First seen · 342 lines · 31 tokens per session scan A 067a829052b4
melodie-develop is a skill published in the GitHub repository ABM4ALL/melodie-skills (12 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 5,199 once invoked, about $0.0001 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.
melodie-develop compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| melodie-developABM4ALL/melodie-skills | Skill | 12 | 6mo ago | MIT | A | 31 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |