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/dual-agent-fork-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/dual-agent-fork-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/dual-agent-fork-guard/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/dual-agent-fork-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/dual-agent-fork-guard.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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
dual-agent-fork-guard 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 12d 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
架构分叉警示（dual-agent-fork-guard）
根因（2026-03-22 消息系统架构设计发现）： 「消息对话」和「proxy模式」本质同构，均为「用户与分身的认知文档对话」， 过早引入独立 MESSAGE_AGENT 造成不必要的代码分叉，最终需要合并。 认知规律：「两套 agent/模块/服务 做同一件事」是架构分叉的警示信号。
核心规则（系统设计/代码实现任务中生效）
检测触发条件（任一满足即触发）：
- 正在创建第二个「与已有X功能高度相似」的 Agent/Skill/模块
- 正在为两条「本质相同的路径」分别实现逻辑
- 发现代码库中两个函数/类的职责有≥70%重叠
检测到时，必须在继续执行前输出警示：
⚠️ [架构分叉检测]
发现 [新组件名] 与 [已有组件名] 可能做同一件事：
新组件：[一句话描述职责]
已有组件：[一句话描述职责]
相同点：[列出3条相同的核心行为]
差异点：[列出真实存在的差异，如无则说明]
建议：
A. 直接复用已有组件（差异通过参数/配置解决）
B. 扩展已有组件（在原有基础上加入差异行为）
C. 确实需要独立组件（请说明无法合并的根本原因）
等待确认后继续。
典型案例（已验证）
案例1：tashan-openbrain 消息系统
- 错误：新建 MESSAGE_AGENT（第一人称消息对话）
- 正确：复用 PROXY_AGENT（同为「与分身的认知文档对话」，仅视角不同）
- 修复：将 messages.py 的
agent_type="message"改为agent_type="proxy"
案例2：「用户上传文档建脑」vs「NPC内容提取」
- 错误：写独立的 extract_npc_content.py 自定义逻辑
- 正确：复用 /twin/build-cognition 端点（同一条认知构建管道）
- 修复：run_npc_init.py 调用相同的代码路径
合并优先级原则
单一代码路径 > 参数化分支 > 继承/组合 > 独立组件
只有满足以下所有条件，才允许创建独立组件：
1. 两者有根本不同的安全边界（如：写入权限不同）
2. 两者的核心算法逻辑无法统一
3. 合并会导致代码复杂度净增加（有量化证据）
变更记录
2026-03-23 — 初始创建
根因：project-retrospective-20260323 E1 类架构级发现。 来源：消息/proxy同构问题（PENDING-EXPERIENCES 2026-03-22 新发现E）。 本 Rule 作为 alwaysApply 约束，在架构设计和代码实现任务中触发分叉检测。
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.
- 12d ago First seen · 76 lines · 806 tokens per session scan A 3870dff3050c
dual-agent-fork-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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.
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.
02-architecture
Architecture rules - MVVM baseline, MVI for complex features.