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 TashanGKD/tashan-cursor-skills --skill modify-theory-systemgit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-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/tashangkd/tashan-cursor-skills/modify-theory-system)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/modify-theory-system"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/modify-theory-system/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/tashangkd/tashan-cursor-skills/modify-theory-system"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/modify-theory-system.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 | $0.00075 | $0.01356 |
| Opus 5 | $0.00037 | $0.00678 |
| Sonnet 5 | $0.00015 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
modify-theory-system 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 8d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术体系修改技能
警告：修改①②是最高优先级操作，必须严格按7阶段流程执行。任何绕过本流程的修改都是违规的。
最小修改原则（动手前先判断）
按优先级从高到低，只有当前选项无法解决时才考虑下一级：
优先级1：给已有粒子增加状态变量维度（最低冲击）
优先级2：修改已有规则的条件或动作（不增加新规则）
优先级3：增加新规则（仅当存在"规则漏洞"时允许）
→ 规则漏洞：合法初始状态 + 合法事件 → 现有规则无法给出唯一合法结果
优先级4：增加新粒子类型（极端情况，需专项论证）
必须在 ISSUE 文档中写明"为什么当前优先级无法解决"才能选更低优先级。
7 阶段执行流程
阶段 0：触发确认
明确触发来源：
- 沙盘推演发现实现缺口（场景D）
- 沙盘推演发现理论缺口（场景E）
- 开发过程主动发现
阶段 1：建立 ISSUE 文档（动手前必须完成）
在对应仓库的 issues/ 目录创建：ISSUE-YYYYMMDD-NN.md
文档必须包含：
- 问题描述（现象、复现步骤、根因层定位）
- 优先级判断过程（逐级排查，说明为什么选当前级别）
- 方案描述（精确到字段/规则级别）
- 逻辑自洽性证据（T层目标 + 相关PA层公理逐条核查）
检查清单（全部勾选才能进入阶段2）：
- 问题描述清晰，可被复现
- 根因定位到具体层（T/PA/G）
- 方案选择过程完整（按优先级从高到低排查）
- 逻辑自洽性证据逐条写完
- 最小修改原则的判断结论已写明
阶段 2：版本复制
# 在修改之前先保留旧版本
cp 三粒子体系结构_v2.1.md 三粒子体系结构_v2.2.md
# 在新版本上修改，旧版本永久保留
版本号规则：
| 修改类型 | 版本位变化 |
|---|---|
| 增加变量维度（向后兼容） | PATCH（+0.0.1） |
| 修改规则条件/动作 | MINOR（+0.1.0） |
| 增加新规则或修改PA层 | MINOR（+0.1.0） |
| 修改T层目标或增加粒子 | MAJOR（+1.0.0） |
阶段 3：执行修改
严格按 ISSUE 文档中的方案执行。
每改一处，立即在 ISSUE 文档的「修改过程记录」追加（不是改完汇总）：
### 修改点 [序号]：[位置简述]
**文件**：xxx_vA.B.D.md
**位置**：第X节
**修改前**：（精确引用）
**修改后**：（新内容）
**原因**：与方案的对应关系
阶段 4：回归沙盘验证
必须验证的范围：
| 修改类型 | 验证范围 |
|---|---|
| 增加粒子变量维度 | 所有涉及该粒子的现有场景 |
| 修改G层规则 | 全集扫描（标注"无关"的需说明） |
| 修改PA层公理 | 全量场景（无一例外） |
| 修改T层目标 | 全量场景 + 专项论证 |
阶段 5：自洽性声明
在 ISSUE 文档中逐条声明：
- 每条 T 层目标：无影响 / 正向加强 / 修改但仍满足
- 相关 PA 层公理：逐条核查
- 其他G层要求：是否有冲突或适配措施
不允许模糊表述（"整体上不违反"不可接受，必须逐条引用）。
阶段 6：联动触发
| 修改类型 | 必须触发 |
|---|---|
| 修改了①公理体系 | 场景F → A（通知②） + B（通知③） |
| 修改了②体系结构 | 场景G（通知TF架构合规层） |
| 修改了②且影响Bᵢ | 场景K（通知④⑤分身系统） |
执行联动通知，参见技能 trigger-linkage-rules/SKILL.md。
阶段 7：ISSUE 归档
在 ISSUE 文档末尾填写完成记录：
- 完成日期
- 最终版本号
- 通过的沙盘场景列表
- 已触发的联动场景编号
- 遗留事项
然后在 任务日志.md 追加一条日志记录，参见技能 write-task-log/SKILL.md。
相关规范
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.
- 8d ago First seen · 147 lines · 75 tokens per session scan A 8d1777f6d749
modify-theory-system is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,356 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
android-preflight
Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…
qa
QA lead testing mode with browser automation. Tests affected pages, fills forms, takes screenshots. Use when user says /qa, wants to test the app, needs QA verification, or wants browser-based testing.
chaos
Failure injection — stress test implementations under hostile conditions before shipping.
qa
Systematic QA pass — test the feature, find bugs, report with repro steps.
template-helpers
Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…
android-feature
Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…