ln-010-dev-environment-setup

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Paths: File paths (
shared/
,
references/
,
../ln-*
) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

路径说明： 文件路径（
shared/
、
references/
、
../ln-*
）均相对于技能仓库根目录。如果在当前工作目录找不到，请定位到当前SKILL.md文件所在目录，向上返回一级即为仓库根目录。

Dev Environment Setup

开发环境搭建

Type: L2 Domain Coordinator Category: 0XX Shared

Runtime-backed coordinator for environment setup. The runtime is the execution SSOT. Worker outputs are standalone summaries, not chat prose.

类型： L2 域协调器 分类： 0XX 共享类

基于运行时的环境搭建协调器，运行时是执行的唯一真实源（SSOT）。工作器输出为独立摘要，而非对话式文本。

MANDATORY READ

必读内容

Load these before execution:

shared/references/coordinator_runtime_contract.md

shared/references/environment_setup_runtime_contract.md

shared/references/coordinator_summary_contract.md

shared/references/environment_state_contract.md

shared/references/environment_state_schema.json

```
shared/references/tools_config_guide.md
```

执行前请加载以下文件：

shared/references/coordinator_runtime_contract.md

shared/references/environment_setup_runtime_contract.md

shared/references/coordinator_summary_contract.md

shared/references/environment_state_contract.md

shared/references/environment_state_schema.json

```
shared/references/tools_config_guide.md
```

When to Use

使用场景

First-time environment setup
Agent/MCP drift after installs or updates
Config sync drift across Claude, Gemini, Codex
Instruction file audit or repair

首次环境搭建
安装或更新后出现Agent/MCP漂移
Claude、Gemini、Codex之间的配置同步漂移
指令文件审计或修复

Inputs

输入参数

Parameter	Required	Default	Description
`targets`	No	`both`	`gemini` , `codex` , or `both`
`dry_run`	No	`false`	Plan without mutating

参数	是否必填	默认值	描述
`targets`	否	`both`	`gemini` 、 `codex` 或 `both`
`dry_run`	否	`false`	仅输出执行计划，不实际修改配置

Runtime

运行时

Runtime family:

environment-setup-runtime

Identifier:

```
targets-{normalizedTargets}
```

Phases:

```
PHASE_0_CONFIG
```
```
PHASE_1_ASSESS
```
```
PHASE_2_DISPATCH_PLAN
```
```
PHASE_3_WORKER_EXECUTION
```
```
PHASE_4_VERIFY
```
```
PHASE_5_WRITE_ENV_STATE
```
```
PHASE_6_SELF_CHECK
```

Terminal phases:

```
DONE
```
```
PAUSED
```

运行时族：

environment-setup-runtime

标识符：

```
targets-{normalizedTargets}
```

执行阶段：

```
PHASE_0_CONFIG 配置阶段
```
```
PHASE_1_ASSESS 评估阶段
```

PHASE_2_DISPATCH_PLAN 调度计划阶段

PHASE_3_WORKER_EXECUTION 工作器执行阶段

```
PHASE_4_VERIFY 验证阶段
```

PHASE_5_WRITE_ENV_STATE 写入环境状态阶段

```
PHASE_6_SELF_CHECK 自检阶段
```

终止阶段：

```
DONE 已完成
```
```
PAUSED 已暂停
```

Phase Map

阶段详情

Phase 1: Assess

阶段1：评估

Collect one environment snapshot:

agent availability and versions
MCP registration/connection state
hook state
config sync state
instruction file state
disabled flags from
```
.hex-skills/environment_state.json
```
if present

Checkpoint payload:

```
assess_summary
```

采集一份环境快照，包含以下内容：

Agent可用性与版本
MCP注册/连接状态
hook状态
配置同步状态
指令文件状态
若存在
```
.hex-skills/environment_state.json
```
，读取其中的禁用标记

检查点负载：

```
assess_summary 评估摘要
```

Phase 2: Dispatch Plan

阶段2：调度计划

Build selective dispatch plan. Only invoke workers that have work.

Workers:

```
ln-011-agent-installer
```
```
ln-012-mcp-configurator
```
```
ln-013-config-syncer
```
```
ln-014-agent-instructions-manager
```

Checkpoint payload:

```
dispatch_plan
```

构建定向调度计划，仅调用有任务需要执行的工作器。

工作器列表：

```
ln-011-agent-installer
```
```
ln-012-mcp-configurator
```
```
ln-013-config-syncer
```
```
ln-014-agent-instructions-manager
```

检查点负载：

```
dispatch_plan 调度计划
```

Phase 3: Worker Execution

阶段3：工作器执行

Invoke only selected workers. Do not re-probe the whole environment between worker calls.

Each worker:

remains standalone-capable
may receive
```
summaryArtifactPath
```
must return the same structured summary even without artifact writing

Expected summary kinds:

```
env-agent-install
```
```
env-mcp-config
```
```
env-config-sync
```
```
env-instructions
```

Record summaries with runtime

record-worker

仅调用选中的工作器，工作器调用间隔无需重新探测全量环境。

每个工作器：

保持独立运行能力
可接收
```
summaryArtifactPath
```
参数
即使不写入产物，也必须返回相同结构的摘要

预期摘要类型：

```
env-agent-install
```
```
env-mcp-config
```
```
env-config-sync
```
```
env-instructions
```

通过运行时

record-worker

接口记录摘要。

Phase 4: Verify

阶段4：验证

Run targeted verification against the post-worker state:

health checks
hook status
sync status
instruction file quality
runtime dependency status (ripgrep, optional language servers)

Checkpoint payload:

```
verification_summary
```

针对工作器执行后的状态执行定向验证：

健康检查
hook状态
同步状态
指令文件质量
运行时依赖状态（ripgrep、可选的语言服务器）

检查点负载：

```
verification_summary 验证摘要
```

Phase 5: Write Environment State

阶段5：写入环境状态

Write final durable state to:

```
.hex-skills/environment_state.json
```

Rules:

runtime state is not environment state
workers never write
```
.hex-skills/environment_state.json
```
validate output against shared schema before persisting

Checkpoint payload:

```
env_state_written
```
```
final_result
```

将最终持久化状态写入以下路径：

```
.hex-skills/environment_state.json
```

规则：

运行时状态不属于环境状态
工作器永远不得写入
```
.hex-skills/environment_state.json
```
持久化前需对照共享Schema验证输出内容

检查点负载：

```
env_state_written 环境状态已写入
```
```
final_result 最终结果
```

Phase 6: Self-Check

阶段6：自检

Confirm:

every required phase checkpoint exists
dispatched worker summaries were recorded
final state file was written unless
```
dry_run
```

Checkpoint payload:

```
pass
```
```
final_result
```

确认以下内容：

所有必填阶段的检查点均存在
调度的工作器摘要均已记录
若非
```
dry_run
```
模式，最终状态文件已写入

检查点负载：

```
pass 检查通过
```
```
final_result 最终结果
```

Output Policy

输出规则

Runtime artifacts:

.hex-skills/runtime-artifacts/runs/{run_id}/{summary_kind}/{identifier}.json

Durable environment output:

```
.hex-skills/environment_state.json
```

Do not mix these layers.

运行时产物路径：

.hex-skills/runtime-artifacts/runs/{run_id}/{summary_kind}/{identifier}.json

持久化环境输出路径：

```
.hex-skills/environment_state.json
```

请勿混合这两层输出。

Worker Invocation (MANDATORY)

工作器调用规则（强制要求）

Phase	Worker	Context
3	`ln-011-agent-installer`	Install or update CLI agents
3	`ln-012-mcp-configurator`	Configure MCP servers, hooks, and permissions
3	`ln-013-config-syncer`	Sync config to Gemini and Codex
3	`ln-014-agent-instructions-manager`	Create and audit instruction files

text

Skill(skill: "ln-011-agent-installer", args: "{targets} {dry_run}")
Skill(skill: "ln-012-mcp-configurator", args: "{dry_run}")
Skill(skill: "ln-013-config-syncer", args: "{targets} {dry_run}")
Skill(skill: "ln-014-agent-instructions-manager", args: "{dry_run}")

阶段	工作器	上下文
3	`ln-011-agent-installer`	安装或更新CLI Agent
3	`ln-012-mcp-configurator`	配置MCP服务器、hook与权限
3	`ln-013-config-syncer`	同步配置到Gemini和Codex
3	`ln-014-agent-instructions-manager`	创建并审计指令文件

text

Skill(skill: "ln-011-agent-installer", args: "{targets} {dry_run}")
Skill(skill: "ln-012-mcp-configurator", args: "{dry_run}")
Skill(skill: "ln-013-config-syncer", args: "{targets} {dry_run}")
Skill(skill: "ln-014-agent-instructions-manager", args: "{dry_run}")

TodoWrite format (mandatory)

待办写入格式（强制要求）

text

- Phase 1: Assess (pending)
- Phase 2: Build dispatch plan (pending)
- Phase 3: Run selected workers (pending)
- Phase 4: Verify final state (pending)
- Phase 5: Write environment_state.json (pending)
- Phase 6: Self-check (pending)

text

- Phase 1: Assess (pending)
- Phase 2: Build dispatch plan (pending)
- Phase 3: Run selected workers (pending)
- Phase 4: Verify final state (pending)
- Phase 5: Write environment_state.json (pending)
- Phase 6: Self-check (pending)

Critical Rules

关键规则

Runtime state is the execution SSOT.
Do not rely on chat memory for resume or recovery.
Do not run non-selected workers.
Do not repeat full-environment discovery after every worker.
```
.hex-skills/environment_state.json
```
is written only in Phase 5.
```
dry_run
```
may end with
```
final_result=DRY_RUN_PLAN
```
and skip final state write.

运行时状态是执行的唯一真实源(SSOT)
不要依赖对话记忆进行任务恢复或续跑
不要运行未被选中的工作器
不要在每个工作器执行后重复全量环境探测
```
.hex-skills/environment_state.json
```
仅可在阶段5写入
```
dry_run
```
模式下最终结果会返回
```
DRY_RUN_PLAN
```
，跳过最终状态写入

Definition of Done

完成定义

Runtime started with identifier-scoped manifest and state
Assessment snapshot recorded
Dispatch plan checkpointed
Worker summaries recorded through machine-readable contract
Verification summary checkpointed

.hex-skills/environment_state.json

validated and written, or explicit

DRY_RUN_PLAN

Self-check passed

运行时已使用标识符范围的清单和状态启动
评估快照已记录
调度计划已存入检查点
工作器摘要已通过机器可读协议记录
验证摘要已存入检查点

.hex-skills/environment_state.json

已验证并写入，或显式返回

DRY_RUN_PLAN

自检通过

Meta-Analysis

元分析

MANDATORY READ: Load

shared/references/meta_analysis_protocol.md

Skill type:

domain-coordinator

. Run after all phases complete. Output to chat using the protocol format.

Version: 5.0.0 Last Updated: 2026-03-24

必读： 加载

shared/references/meta_analysis_protocol.md

技能类型：

domain-coordinator

。所有阶段完成后运行，按照协议格式输出到对话中。

版本： 5.0.0 最后更新： 2026-03-24