workspace-isolation
Skill220 starsChanged 8 days agoMITView on GitHub
按执行实例准备、核验和回收worktree与实际sandbox，缺后端时拒绝，不把目录当隔离。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- NoobyGains/godmodetheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- NoobyGains/godmode★ 118same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- capability-evaluationSkill
- code-implementationSkill
- code-reviewSkill
- conclusion-challengeSkill
- delivery-planningSkill
- docker-build-isolationSkill
- document-maintenanceSkill
- document-reviewSkill
- evidence-collectionSkill
- evidence-diagnosisSkill
- java-build-isolationSkill
- java-spring-checkSkill
- module-planningSkill
- principle-reviewSkill
- requirement-clarificationSkill
- semantic-reviewSkill
- sql-reviewSkill
- task-executionSkill
- technical-design-reviewSkill
- technical-designSkill
- verificationSkill
The file
Files
目的：将当前任务边界适配到可验证的执行实例与资源，保护已有工作区。
适用于：需要并发写入或保护现有工作区且宿主提供已验证后端的任务。
工作区隔离
适用与输入
需要并发写入或保护现有工作区时采用；输入为可信仓库、冻结提交、run_id/父子关系、运行根、工具只读根、写集与有限预算。调用者须明确这些目录和动作已授权。
共用方法
- 执行实例隔离
- 并发与候选合同
实际步骤
- 核来源和干净快照；不stash用户改动，也不凭HEAD猜未提交代码。当前实现拒属性过滤器、子模块和符号链接来源。
- 通过宿主资源机制分配独立branch/worktree/HOME/TMP；不把宿主凭证、Git管理目录和相邻实例挂载给作业。
- 调用实际macOS内核后端并探测读写/网络/Git/链接/派生进程边界；不支持即拒绝，未知不能填通过。
- 执行已声明前台argv，单写状态和有限预算由宿主控制。当前默认禁止fork，Maven/Gradle等需要子进程的命令不可直接使用此后端。
- 作业结束核字节/HEAD/index/写集；仅宿主提交，并在集成候选重验。回收只处理干净、身份一致的已停止资源。
输出与停止
交资源归属、探测、输入/输出提交、状态与未决；实际源码/日志默认私有，不因产出自动公开。超时/取消终止已知进程组；UNKNOWN占用不自动释放或重试，整个池隔离后需人工核外部状态。审计检查不等于自动续跑。
能力边界
仅已测macOS sandbox-exec实验前台后端，该命令已弃用；无Linux/Windows裸进程回退。文件元数据/根目录枚举及声明工具根只读允许，不提供恶意多租户、总RAM/总磁盘硬配额或宿主SIGKILL后自动进程回收保证。共享额度只覆盖采用同一runtime_root的本引擎实例；别的运行根和外部进程不计入。
具体案例由上层Graph组织：Graph案例。返回：Skills。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.