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.
git 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/rules/tashangkd/tashan-cursor-skills/tech-discovery-capture)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/tech-discovery-capture"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/tech-discovery-capture/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/rules/tashangkd/tashan-cursor-skills/tech-discovery-capture"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/tech-discovery-capture.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 | $0.00068 | $0.01042 |
| Opus 5 | $0.00034 | $0.00521 |
| Sonnet 5 | $0.00014 | $0.00208 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
tech-discovery-capture 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 9d 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.
What it actually says
技术发现捕捉规则（tech-discovery-capture）
目的：把「踩坑」和「点石成金」都沉淀下来——前者靠踩坑速查，后者靠本规则。
信号一：不确定方案 → 先搜索，再动手
触发条件（满足任一即触发）：
- 对某个 API / 库的用法不确定（「这个参数该怎么传？」）
- 遇到两个可行方案，不知道哪个在这个场景更合适
- 遇到不熟悉的报错模式，猜不准根因
- 要在多种技术选型中取舍（「用 A 还是 B？」）
执行动作（必须在写代码前完成）：
1. 调用 WebSearch，搜索至少 2 个角度：
- 「[具体问题] best practice site:stackoverflow.com OR github.com」
- 「[库名] [场景] 2025 OR 2026」（用当年年份确保时效性）
- 「[错误信息] fix」
2. 综合搜索结果 → 形成方案假设 → 再动手
3. 若搜索结果与已有踩坑速查冲突 → 以踩坑速查为准（来自实际验证）
不触发的情况：
- 问题在踩坑速查中已有明确答案 → 直接用，不需要搜索
- 方案完全确定，无任何不确定性 → 跳过
信号二：高价值技术发现 → 调用子智能体写文档
触发条件（满足以下任意 2 条即触发）：
- 技术含量高（涉及并发/安全/性能/协议/底层机制的精妙处理）
- 网上难找（搜索后没有现成方案，需要自己推导或组合）
- 有巧思（以小改动解决大问题，或以非常规方式绕过框架限制）
- 生产/集成测试中已验证通过（不是理论方案）
执行动作：
调用 generalPurpose 子智能体，传入：
task: 「写一份技术发现文档」
context:
- 问题背景：[完整描述]
- 解决方案：[完整描述 + 关键代码]
- 对比方案：[为什么没用其他方案]
- 验证方式：[如何确认它有效]
template: _内部总控/认知结构/L1_系统性文档/技术架构思维维度/知识库/_技术发现文档_TEMPLATE.md
output_dir: _内部总控/认知结构/L1_系统性文档/技术架构思维维度/知识库/
requirement:
- 文档必须包含架构图或流程图（ASCII 为主，有必要时附 canvas 可视化）
- 文件名格式：YYYY-MM-DD_[方案简称].md
- 写完后在 PENDING-EXPERIENCES.md 追加一行（信号B：新发现），标注「已写详细文档」
判断提示：
- 「这个方案下次换个项目还能直接用」→ 值得写
- 「这是专门针对我们项目某个奇怪问题的一次性 workaround」→ 不写，追加踩坑速查即可
与其他组件的关系
| 组件 | 关系 |
|---|---|
auto-experience-hook |
本规则补充后者：后者写一行暂存，本规则对高价值发现写完整文档（两者不互斥） |
skill-capture-closure |
后者处理 Skill 层经验；本规则处理技术实现层经验 |
踩坑速查.md（后端/前端） |
记录「已知的坑」；本规则记录「有创新价值的新发现」 |
| 技术洞察库 | 本规则的产出存储在 _内部总控/认知结构/L1_系统性文档/技术架构思维维度/知识库/（REF-EXT） |
变更记录
| 日期 | 内容 |
|---|---|
| 2026-03-19 | 初始创建，覆盖「不确定先搜索」（信号一）和「高价值发现写文档」（信号二）两个触发机制 |
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.
- 9d ago First seen · 90 lines · 68 tokens per session scan A d847ed28f92e
tech-discovery-capture is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 1,042 once invoked, about $0.0003 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 cursor rules, from other repositories
10-feature-development
Feature implementation workflow and engineering mindset.
11-template-conventions
Reusable building blocks shipped with this template - use them instead of writing new ones.
03-ui
UI, layout, theming and localization standards.
12-new-project
Workflow for starting a new app from this template - rebranding, identity, cleanup and first feature.
13-updating-project
Workflow for updating an existing project - dependency and SDK upgrades, migrations, refactors, bug fixes.
01-tech-stack
Android tech stack and project standards.