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/co-build-log)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/co-build-log"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/co-build-log/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/co-build-log"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/co-build-log.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 | $0.00131 | $0.00921 |
| Opus 5 | $0.00066 | $0.00461 |
| Sonnet 5 | $0.00026 | $0.00184 |
| Haiku 4.5 | $0.00013 | $0.00092 |
Grade A, and why
co-build-log 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 10d 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
协作建设日志（co-build-log）
目的：让 project-retrospective 复盘时不只能看到「发生了什么」，还能看到「为什么这样做」。 过程日志是最有提炼价值的隐性知识来源。
触发信号（满足任一条即触发写入）
仅在以下「创作型任务」场景中生效，普通执行任务不触发：
信号 I：任务启动宣告
→ 用户明确说「要构建/重做/设计」某个新机制、新 Skill、新架构
→ AI 开始一个显著不同于已有模式的新方案
→ 记录：用户的设计意图 + AI 理解的核心问题
信号 II：重大方案提出
→ AI 提出一个有多个候选方案的设计决策
→ AI 在多个选项中做了取舍
→ 记录：方案内容 + 取舍理由 + 未选择的备选方案
信号 III：方案被否定/修正
→ 用户说「不对」「换个思路」「这样不行」
→ 某个方向执行后发现根本性问题需要推翻
→ 记录：被否定的方案 + 否定原因 + 新方向假设
信号 IV：意外发现
→ 执行过程中发现一个之前完全没想到的约束或可能性
→ 这个发现影响了后续所有决策
→ 记录：发现内容 + 对原方案的影响 + 新的推论
信号 V：任务完成
→ 一个完整的协作建设任务结束
→ 记录：最终方案概要 + 与初始意图的差异 + 核心洞见
不触发的情况（避免噪音）：
- 执行已有 Skill 的标准步骤
- 常规配置修改、格式调整
- 用户只是询问信息（不是在建设什么）
写入操作（触发后立即执行，不阻断主任务）
调用 /co-build-logger 后台子智能体，传入：
- 信号类型：I/II/III/IV/V
- 任务名称：[当前正在构建的是什么]
- 用户意图：[用户说了什么或表达了什么]（可为空）
- AI推理：[AI提出方案的理由，或理解用户意图的推理]
- 关键内容：[方案概要/否定理由/发现内容/完成总结]
- 今日日期：YYYY-MM-DD HH:MM
继续主任务（子智能体在后台异步写入，主对话不感知）
与 auto-experience-hook 的边界
| auto-experience-hook | co-build-log | |
|---|---|---|
| 捕捉对象 | 结果（踩坑、新发现、步骤偏差） | 过程（推理链、决策轨迹、转折理由） |
| 触发时机 | 遇到具体错误或发现时 | 重大决策点、方向转折时 |
| 记录粒度 | 一行 | 多行（含推理过程） |
| 读取时机 | project-retrospective Step 2（路1） | project-retrospective Step 2（路3） |
两者不互斥，一个事件可以同时触发两者（如「试错失败」既有结果[踩坑]也有过程[为什么尝试这个方案]）。
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.
- 10d ago First seen · 76 lines · 131 tokens per session scan A 3d6f5dec1cc7
co-build-log is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 131 tokens to every session and 921 once invoked, about $0.0007 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.