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/tellmewhattodo/theory-eap/opencode-skillnpx skills add tellmewhattodo/theory-eap --skill opencode-skillgit clone --depth 1 https://github.com/tellmewhattodo/theory-eapWrote 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/tellmewhattodo/theory-eap/opencode-skill)<a href="https://agentmods.dev/skills/tellmewhattodo/theory-eap/opencode-skill"><img src="https://agentmods.dev/badge/skills/tellmewhattodo/theory-eap/opencode-skill.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.03530 |
| Opus 5 | $0.00045 | $0.01765 |
| Sonnet 5 | $0.00018 | $0.00706 |
| Haiku 4.5 | $0.00009 | $0.00353 |
Grade A, and why
eap 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 3d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EAP — Explicit Abstraction Principle
什么是 EAP
EAP（Explicit Abstraction Principle，显式抽象原则）是一个关于"思维在 LLM 时代如何获得功能价值"的理论框架。其核心命题是：
思维的功能价值，与其外部可重建性成正比。
在 LLM 主导的认知环境中，思维如果停留在内部、不可外部化，就无法被 LLM 接收、处理和执行——它变得不可操作。因此，构建显式抽象的能力正在成为 LLM 时代最关键的元能力。
本 skill 将 EAP 理论注入 Agent 行为模式，使 Agent 在感知到用户表达显式度不足时，主动介入并引导用户完成隐式→显式的转化。
何时加载本 Skill
当以下信号出现时，你应当加载本 skill 并进入 EAP 模式：
显式度不足的信号
| 信号 | 用户输入示例 | EAP 判断 |
|---|---|---|
| 缺少关键变量 | "系统应该快" | 没有定义"快"的量化指标，E 极低 |
| 隐含假设 | "用常规方案就行" | "常规"是什么？不同人的理解不同，S 极低 |
| 依赖共享上下文 | "你懂的，就是那个" | LLM 没有你的共享上下文，无法重建 |
| 层级跳跃 | "给我做个登录" | 从最高抽象直接跳到实现，中间缺少多层约束 |
| 模糊关系 | "A 和 B 关联" | 关联类型/方向/基数/条件均未定义 |
| 压缩表达 | "加个字段" | 字段名/类型/默认值/含义均未指定 |
| 歧义词汇 | "处理一下这个问题" | "处理"是修 bug/加功能/改配置/删数据？"问题"是 bug/需求/疑问？ |
| 缺失边界 | "支持更多用户" | 多少算"更多"？从多少到多少？场景是什么？ |
| 缺乏验收标准 | "做好就行" | "好"的标准是什么？谁来判断？ |
| 过早细节 | 在高层抽象未对齐时讨论具体实现 | 控制论陷阱：过早进入"如何做"而跳过"是什么/为什么" |
判断准则
当以下任一条件成立时，进入 EAP 模式：
- 用户提供的信息量 I'(T) 明显小于完成任务所需的信息量——即表达中存在大量被压缩/省略/隐含的结构，LLM 的重建成本 R 过高
- 同一段话可以有两种以上合理的解释——即稳定性 S 过低，不同接收者会重建出不同的理解
- 你需要依赖"猜测"或"假设"来补全用户的意图——说明用户的隐式抽象（Implicit Abstraction）占主导
- 用户使用了高歧义词汇且没有在上下文中锁定其含义——如"问题"、"处理"、"优化"、"重构"、"支持"、"接口"
- 用户的请求跨多个层级但没有显式说明层级关系——从需求直接跳到代码，缺少中间的方案/设计/接口层级
EAP 核心框架
三个核心变量
在评估任何认知表达时，使用这三个维度：
| 变量 | 含义 | 低值表现 | 高值表现 |
|---|---|---|---|
| E (显式度) | 有多少结构被外部编码 | 依赖隐含上下文，变量未定义 | 变量明确，关系编码，步骤可恢复 |
| R (重建成本) | 外部系统恢复意义所需的代价 | 需要大量猜测/补全/追问 | 可被直接解析和执行 |
| S (稳定性) | 不同系统对同一表达的重建一致程度 | 十个人有十种理解 | 所有接收者得到相同的结构 |
EAP 原则：功能价值随 E↑、R↓、S↑ 而最大化。
显式 vs 隐式 vs 重建
- 显式抽象 (Explicit Abstraction)：变量明确定义、关系结构性编码、推理步骤可被外部系统恢复。结构独立于任何特定接收者。
- 隐式抽象 (Implicit Abstraction)：结构被压缩或省略、意义依赖共享上下文、重建需要接收者进行内部推理。
- 外部重建 (External Reconstruction)：外部系统从表达中恢复结构、重现推理步骤、维持语义等价的过程。
信息论视角优先
EAP 实践中，始终优先使用信息论视角（关注信息结构本身的质量），而不是控制论视角（关注对话反馈回路）。先确保每一层的信息质量（E↑、R↓、S↑），再考虑如何通过反馈回路持续改进。这是 Neat 方法论的理论基础：结构性质问的目的不是"对话"，而是"提高表达的显式度"。
EAP 实践指南
当你进入 EAP 模式后，按以下步骤引导用户提升表达质量：
What ships with it
2 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.
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.
- 3d ago First seen · 263 lines · 90 tokens per session scan A adbbfa450e11
eap is a skill published in the GitHub repository tellmewhattodo/theory-eap (11 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 3,530 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
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…