Claude Code 插件设置配置教程 - YAML Frontmatter 与 Markdown 状态管理

Plugin Settings by davila7/claude-code-templates

22,600 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/davila7/claude-code-templates --skill 'Plugin Settings'

开发自动化开发运维

🇨🇳中文介绍

Claude Code 插件的设置模式

概述

插件可以在项目目录的 .claude/plugin-name.local.md 文件中存储用户可配置的设置和状态。此模式使用 YAML frontmatter 进行结构化配置，并使用 markdown 内容作为提示或附加上下文。

主要特性：

文件位置：项目根目录中的 .claude/plugin-name.local.md
结构：YAML frontmatter + markdown 正文
目的：每个项目的插件配置和状态
用法：从钩子、命令和代理中读取
生命周期：用户管理（不在 git 中，应放在 .gitignore 中）

文件结构

基本模板

---
enabled: true
setting1: value1
setting2: value2
numeric_setting: 42
list_setting: ["item1", "item2"]
---

# 附加上下文

此 markdown 正文可以包含：
- 任务描述
- 附加说明
- 反馈给 Claude 的提示
- 文档或笔记

示例：插件状态文件

.claude/my-plugin.local.md:

---
enabled: true
strict_mode: false
max_retries: 3
notification_level: info
coordinator_session: team-leader
---

# 插件配置

此插件已配置为标准验证模式。
如有疑问，请联系 @team-lead。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

从钩子中读取（Bash 脚本）

模式：检查存在性并解析 frontmatter

#!/bin/bash
set -euo pipefail

# 定义状态文件路径
STATE_FILE=".claude/my-plugin.local.md"

# 如果文件不存在，快速退出
if [[ ! -f "$STATE_FILE" ]]; then
  exit 0  # 插件未配置，跳过
fi

# 解析 YAML frontmatter（在 --- 标记之间）
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$STATE_FILE")

# 提取各个字段
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//' | sed 's/^"\(.*\)"$/\1/')
STRICT_MODE=$(echo "$FRONTMATTER" | grep '^strict_mode:' | sed 's/strict_mode: *//' | sed 's/^"\(.*\)"$/\1/')

# 检查是否启用
if [[ "$ENABLED" != "true" ]]; then
  exit 0  # 已禁用
fi

# 在钩子逻辑中使用配置
if [[ "$STRICT_MODE" == "true" ]]; then
  # 应用严格验证
  # ...
fi

完整工作示例请参见 examples/read-settings-hook.sh。

命令可以读取设置文件以自定义行为：

---
description: 使用插件处理数据
allowed-tools: ["Read", "Bash"]
---

# 处理命令

步骤：
1. 检查 `.claude/my-plugin.local.md` 处是否存在设置
2. 使用 Read 工具读取配置
3. 解析 YAML frontmatter 以提取设置
4. 将设置应用于处理逻辑
5. 使用配置的行为执行

代理可以在其指令中引用设置：

---
name: configured-agent
description: 适应项目设置的代理
---

检查 `.claude/my-plugin.local.md` 处的插件设置。
如果存在，解析 YAML frontmatter 并根据以下内容调整行为：
- enabled: 插件是否处于活动状态
- mode: 处理模式（严格、标准、宽松）
- 其他配置字段

# 提取 --- 标记之间的所有内容
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")

字符串字段：

VALUE=$(echo "$FRONTMATTER" | grep '^field_name:' | sed 's/field_name: *//' | sed 's/^"\(.*\)"$/\1/')

ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
# 比较：if [[ "$ENABLED" == "true" ]]; then

MAX=$(echo "$FRONTMATTER" | grep '^max_value:' | sed 's/max_value: *//')
# 使用：if [[ $MAX -gt 100 ]]; then

读取 Markdown 正文

提取第二个 --- 之后的内容：

# 获取结束 --- 之后的所有内容
BODY=$(awk '/^---$/{i++; next} i>=2' "$FILE")

模式 1：临时活动钩子

使用设置文件控制钩子激活：

#!/bin/bash
STATE_FILE=".claude/security-scan.local.md"

# 如果未配置，快速退出
if [[ ! -f "$STATE_FILE" ]]; then
  exit 0
fi

# 读取启用标志
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$STATE_FILE")
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')

if [[ "$ENABLED" != "true" ]]; then
  exit 0  # 已禁用
fi

# 运行钩子逻辑
# ...

使用场景： 无需编辑 hooks.json 即可启用/禁用钩子（需要重启）。

模式 2：代理状态管理

存储代理特定的状态和配置：

.claude/multi-agent-swarm.local.md:

---
agent_name: auth-agent
task_number: 3.5
pr_number: 1234
coordinator_session: team-leader
enabled: true
dependencies: ["Task 3.4"]
---

# 任务分配

为 API 实现 JWT 身份验证。

**成功标准：**
- 创建身份验证端点
- 测试通过
- 创建 PR 且 CI 通过

从钩子中读取以协调代理：

AGENT_NAME=$(echo "$FRONTMATTER" | grep '^agent_name:' | sed 's/agent_name: *//')
COORDINATOR=$(echo "$FRONTMATTER" | grep '^coordinator_session:' | sed 's/coordinator_session: *//')

# 向协调器发送通知
tmux send-keys -t "$COORDINATOR" "Agent $AGENT_NAME completed task" Enter

模式 3：配置驱动行为

.claude/my-plugin.local.md:

---
validation_level: strict
max_file_size: 1000000
allowed_extensions: [".js", ".ts", ".tsx"]
enable_logging: true
---

# 验证配置

此项目已启用严格模式。
所有写入都根据安全策略进行验证。

在钩子或命令中使用：

LEVEL=$(echo "$FRONTMATTER" | grep '^validation_level:' | sed 's/validation_level: *//')

case "$LEVEL" in
  strict)
    # 应用严格验证
    ;;
  standard)
    # 应用标准验证
    ;;
  lenient)
    # 应用宽松验证
    ;;
esac

命令可以创建设置文件：

# 设置命令

步骤：
1. 向用户询问配置偏好
2. 使用 YAML frontmatter 创建 `.claude/my-plugin.local.md`
3. 根据用户输入设置适当的值
4. 通知用户设置已保存
5. 提醒用户重启 Claude Code 以使钩子识别更改

在插件 README 中提供模板：

## 配置

在您的项目中创建 `.claude/my-plugin.local.md`：

\`\`\`markdown
---
enabled: true
mode: standard
max_retries: 3
---

# 插件配置

您的设置已生效。
\`\`\`

创建或编辑后，重启 Claude Code 以使更改生效。

使用 .claude/plugin-name.local.md 格式
与插件名称完全匹配
对用户本地文件使用 .local.md 后缀

❌ 不应该：

使用不同的目录（不是 .claude/）
使用不一致的命名
使用不带 .local 的 .md（可能会被提交）

始终添加到 .gitignore：

.claude/*.local.md
.claude/*.local.json

在插件 README 中记录这一点。

当设置文件不存在时，提供合理的默认值：

if [[ ! -f "$STATE_FILE" ]]; then
  # 使用默认值
  ENABLED=true
  MODE=standard
else
  # 从文件读取
  # ...
fi

MAX=$(echo "$FRONTMATTER" | grep '^max_value:' | sed 's/max_value: *//')

# 验证数字范围
if ! [[ "$MAX" =~ ^[0-9]+$ ]] || [[ $MAX -lt 1 ]] || [[ $MAX -gt 100 ]]; then
  echo "⚠️  设置中的 max_value 无效（必须为 1-100）" >&2
  MAX=10  # 使用默认值
fi

重要： 设置更改需要重启 Claude Code。

在您的 README 中记录：

## 更改设置

编辑 `.claude/my-plugin.local.md` 后：
1. 保存文件
2. 退出 Claude Code
3. 重启：`claude` 或 `cc`
4. 新设置将被加载

钩子无法在会话内热交换。

从用户输入写入设置文件时：

# 转义用户输入中的引号
SAFE_VALUE=$(echo "$USER_INPUT" | sed 's/"/\\"/g')

# 写入文件
cat > "$STATE_FILE" <<EOF
---
user_setting: "$SAFE_VALUE"
---
EOF

如果设置包含文件路径：

FILE_PATH=$(echo "$FRONTMATTER" | grep '^data_file:' | sed 's/data_file: *//')

# 检查路径遍历
if [[ "$FILE_PATH" == *".."* ]]; then
  echo "⚠️  设置中的路径无效（路径遍历）" >&2
  exit 2
fi

仅用户可读（chmod 600）
不提交到 git
不在用户之间共享

multi-agent-swarm 插件

.claude/multi-agent-swarm.local.md:

---
agent_name: auth-implementation
task_number: 3.5
pr_number: 1234
coordinator_session: team-leader
enabled: true
dependencies: ["Task 3.4"]
additional_instructions: Use JWT tokens, not sessions
---

# 任务：实现身份验证

为 REST API 构建基于 JWT 的身份验证。
与 auth-agent 协调共享类型。

钩子用法（agent-stop-notification.sh）：

检查文件是否存在（第 15-18 行：如果不存在则快速退出）
解析 frontmatter 以获取 coordinator_session、agent_name、enabled
如果启用，向协调器发送通知
允许通过 enabled: true/false 快速激活/停用

.claude/ralph-loop.local.md:

---
iteration: 1
max_iterations: 10
completion_promise: "All tests passing and build successful"
---

修复项目中的所有 linting 错误。
确保每次修复后测试通过。

钩子用法（stop-hook.sh）：

检查文件是否存在（第 15-18 行：如果不活动则快速退出）
读取迭代次数和 max_iterations
提取 completion_promise 以终止循环
读取正文作为反馈的提示
每次循环更新迭代次数

project-root/
└── .claude/
    └── plugin-name.local.md

# 提取 frontmatter
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")

# 读取字段
VALUE=$(echo "$FRONTMATTER" | grep '^field:' | sed 's/field: *//' | sed 's/^"\(.*\)"$/\1/')

# 提取正文（第二个 --- 之后）
BODY=$(awk '/^---$/{i++; next} i>=2' "$FILE")

if [[ ! -f ".claude/my-plugin.local.md" ]]; then
  exit 0  # 未配置
fi

有关详细的实现模式：

references/parsing-techniques.md - 解析 YAML frontmatter 和 markdown 正文的完整指南
references/real-world-examples.md - 深入探讨 multi-agent-swarm 和 ralph-wiggum 的实现

examples/ 中的工作示例：

read-settings-hook.sh - 读取并使用设置的钩子
create-settings-command.md - 创建设置文件的命令
example-settings.md - 模板设置文件

scripts/ 中的开发工具：

validate-settings.sh - 验证设置文件结构
parse-frontmatter.sh - 提取 frontmatter 字段

要为插件添加设置：

设计设置模式（哪些字段、类型、默认值）
在插件文档中创建模板文件
为 .claude/*.local.md 添加 gitignore 条目
在钩子/命令中实现设置解析
使用快速退出模式（检查文件是否存在，检查启用字段）
在插件 README 中记录设置并附带模板
提醒用户更改需要重启 Claude Code

专注于保持设置简单，并在设置文件不存在时提供良好的默认值。

🇺🇸English

Plugin Settings Pattern for Claude Code Plugins

Overview

Plugins can store user-configurable settings and state in .claude/plugin-name.local.md files within the project directory. This pattern uses YAML frontmatter for structured configuration and markdown content for prompts or additional context.

Key characteristics:

File location: .claude/plugin-name.local.md in project root
Structure: YAML frontmatter + markdown body
Purpose: Per-project plugin configuration and state
Usage: Read from hooks, commands, and agents
Lifecycle: User-managed (not in git, should be in .gitignore)

File Structure

Basic Template

---
enabled: true
setting1: value1
setting2: value2
numeric_setting: 42
list_setting: ["item1", "item2"]
---

# Additional Context

This markdown body can contain:
- Task descriptions
- Additional instructions
- Prompts to feed back to Claude
- Documentation or notes

Example: Plugin State File

.claude/my-plugin.local.md:

---
enabled: true
strict_mode: false
max_retries: 3
notification_level: info
coordinator_session: team-leader
---

# Plugin Configuration

This plugin is configured for standard validation mode.
Contact @team-lead with questions.

Reading Settings Files

From Hooks (Bash Scripts)

Pattern: Check existence and parse frontmatter

#!/bin/bash
set -euo pipefail

# Define state file path
STATE_FILE=".claude/my-plugin.local.md"

# Quick exit if file doesn't exist
if [[ ! -f "$STATE_FILE" ]]; then
  exit 0  # Plugin not configured, skip
fi

# Parse YAML frontmatter (between --- markers)
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$STATE_FILE")

# Extract individual fields
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//' | sed 's/^"\(.*\)"$/\1/')
STRICT_MODE=$(echo "$FRONTMATTER" | grep '^strict_mode:' | sed 's/strict_mode: *//' | sed 's/^"\(.*\)"$/\1/')

# Check if enabled
if [[ "$ENABLED" != "true" ]]; then
  exit 0  # Disabled
fi

# Use configuration in hook logic
if [[ "$STRICT_MODE" == "true" ]]; then
  # Apply strict validation
  # ...
fi

See examples/read-settings-hook.sh for complete working example.

From Commands

Commands can read settings files to customize behavior:

---
description: Process data with plugin
allowed-tools: ["Read", "Bash"]
---

# Process Command

Steps:
1. Check if settings exist at `.claude/my-plugin.local.md`
2. Read configuration using Read tool
3. Parse YAML frontmatter to extract settings
4. Apply settings to processing logic
5. Execute with configured behavior

From Agents

Agents can reference settings in their instructions:

---
name: configured-agent
description: Agent that adapts to project settings
---

Check for plugin settings at `.claude/my-plugin.local.md`.
If present, parse YAML frontmatter and adapt behavior according to:
- enabled: Whether plugin is active
- mode: Processing mode (strict, standard, lenient)
- Additional configuration fields

Parsing Techniques

Extract Frontmatter

# Extract everything between --- markers
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")

Read Individual Fields

String fields:

VALUE=$(echo "$FRONTMATTER" | grep '^field_name:' | sed 's/field_name: *//' | sed 's/^"\(.*\)"$/\1/')

Boolean fields:

ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
# Compare: if [[ "$ENABLED" == "true" ]]; then

Numeric fields:

MAX=$(echo "$FRONTMATTER" | grep '^max_value:' | sed 's/max_value: *//')
# Use: if [[ $MAX -gt 100 ]]; then

Read Markdown Body

Extract content after second ---:

# Get everything after closing ---
BODY=$(awk '/^---$/{i++; next} i>=2' "$FILE")

Common Patterns

Pattern 1: Temporarily Active Hooks

Use settings file to control hook activation:

#!/bin/bash
STATE_FILE=".claude/security-scan.local.md"

# Quick exit if not configured
if [[ ! -f "$STATE_FILE" ]]; then
  exit 0
fi

# Read enabled flag
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$STATE_FILE")
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')

if [[ "$ENABLED" != "true" ]]; then
  exit 0  # Disabled
fi

# Run hook logic
# ...

Use case: Enable/disable hooks without editing hooks.json (requires restart).

Pattern 2: Agent State Management

Store agent-specific state and configuration:

.claude/multi-agent-swarm.local.md:

---
agent_name: auth-agent
task_number: 3.5
pr_number: 1234
coordinator_session: team-leader
enabled: true
dependencies: ["Task 3.4"]
---

# Task Assignment

Implement JWT authentication for the API.

**Success Criteria:**
- Authentication endpoints created
- Tests passing
- PR created and CI green

Read from hooks to coordinate agents:

AGENT_NAME=$(echo "$FRONTMATTER" | grep '^agent_name:' | sed 's/agent_name: *//')
COORDINATOR=$(echo "$FRONTMATTER" | grep '^coordinator_session:' | sed 's/coordinator_session: *//')

# Send notification to coordinator
tmux send-keys -t "$COORDINATOR" "Agent $AGENT_NAME completed task" Enter

Pattern 3: Configuration-Driven Behavior

.claude/my-plugin.local.md:

---
validation_level: strict
max_file_size: 1000000
allowed_extensions: [".js", ".ts", ".tsx"]
enable_logging: true
---

# Validation Configuration

Strict mode enabled for this project.
All writes validated against security policies.

Use in hooks or commands:

LEVEL=$(echo "$FRONTMATTER" | grep '^validation_level:' | sed 's/validation_level: *//')

case "$LEVEL" in
  strict)
    # Apply strict validation
    ;;
  standard)
    # Apply standard validation
    ;;
  lenient)
    # Apply lenient validation
    ;;
esac

Creating Settings Files

From Commands

Commands can create settings files:

# Setup Command

Steps:
1. Ask user for configuration preferences
2. Create `.claude/my-plugin.local.md` with YAML frontmatter
3. Set appropriate values based on user input
4. Inform user that settings are saved
5. Remind user to restart Claude Code for hooks to recognize changes

Template Generation

Provide template in plugin README:

## Configuration

Create `.claude/my-plugin.local.md` in your project:

\`\`\`markdown
---
enabled: true
mode: standard
max_retries: 3
---

# Plugin Configuration

Your settings are active.
\`\`\`

After creating or editing, restart Claude Code for changes to take effect.

Best Practices

File Naming

✅ DO:

Use .claude/plugin-name.local.md format
Match plugin name exactly
Use .local.md suffix for user-local files

❌ DON'T:

Use different directory (not .claude/)
Use inconsistent naming
Use .md without .local (might be committed)

Gitignore

Always add to .gitignore:

.claude/*.local.md
.claude/*.local.json

Document this in plugin README.

Defaults

Provide sensible defaults when settings file doesn't exist:

if [[ ! -f "$STATE_FILE" ]]; then
  # Use defaults
  ENABLED=true
  MODE=standard
else
  # Read from file
  # ...
fi

Validation

Validate settings values:

MAX=$(echo "$FRONTMATTER" | grep '^max_value:' | sed 's/max_value: *//')

# Validate numeric range
if ! [[ "$MAX" =~ ^[0-9]+$ ]] || [[ $MAX -lt 1 ]] || [[ $MAX -gt 100 ]]; then
  echo "⚠️  Invalid max_value in settings (must be 1-100)" >&2
  MAX=10  # Use default
fi

Restart Requirement

Important: Settings changes require Claude Code restart.

Document in your README:

## Changing Settings

After editing `.claude/my-plugin.local.md`:
1. Save the file
2. Exit Claude Code
3. Restart: `claude` or `cc`
4. New settings will be loaded

Hooks cannot be hot-swapped within a session.

Security Considerations

Sanitize User Input

When writing settings files from user input:

# Escape quotes in user input
SAFE_VALUE=$(echo "$USER_INPUT" | sed 's/"/\\"/g')

# Write to file
cat > "$STATE_FILE" <<EOF
---
user_setting: "$SAFE_VALUE"
---
EOF

Validate File Paths

If settings contain file paths:

FILE_PATH=$(echo "$FRONTMATTER" | grep '^data_file:' | sed 's/data_file: *//')

# Check for path traversal
if [[ "$FILE_PATH" == *".."* ]]; then
  echo "⚠️  Invalid path in settings (path traversal)" >&2
  exit 2
fi

Permissions

Settings files should be:

Readable by user only (chmod 600)
Not committed to git
Not shared between users

Real-World Examples

multi-agent-swarm Plugin

.claude/multi-agent-swarm.local.md:

---
agent_name: auth-implementation
task_number: 3.5
pr_number: 1234
coordinator_session: team-leader
enabled: true
dependencies: ["Task 3.4"]
additional_instructions: Use JWT tokens, not sessions
---

# Task: Implement Authentication

Build JWT-based authentication for the REST API.
Coordinate with auth-agent on shared types.

Hook usage (agent-stop-notification.sh):

Checks if file exists (line 15-18: quick exit if not)
Parses frontmatter to get coordinator_session, agent_name, enabled
Sends notifications to coordinator if enabled
Allows quick activation/deactivation via enabled: true/false

ralph-wiggum Plugin

.claude/ralph-loop.local.md:

---
iteration: 1
max_iterations: 10
completion_promise: "All tests passing and build successful"
---

Fix all the linting errors in the project.
Make sure tests pass after each fix.

Hook usage (stop-hook.sh):

Checks if file exists (line 15-18: quick exit if not active)
Reads iteration count and max_iterations
Extracts completion_promise for loop termination
Reads body as the prompt to feed back
Updates iteration count on each loop

Quick Reference

File Location

project-root/
└── .claude/
    └── plugin-name.local.md

Frontmatter Parsing

# Extract frontmatter
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")

# Read field
VALUE=$(echo "$FRONTMATTER" | grep '^field:' | sed 's/field: *//' | sed 's/^"\(.*\)"$/\1/')

Body Parsing

# Extract body (after second ---)
BODY=$(awk '/^---$/{i++; next} i>=2' "$FILE")

Quick Exit Pattern

if [[ ! -f ".claude/my-plugin.local.md" ]]; then
  exit 0  # Not configured
fi

Additional Resources

Reference Files

For detailed implementation patterns:

references/parsing-techniques.md - Complete guide to parsing YAML frontmatter and markdown bodies
references/real-world-examples.md - Deep dive into multi-agent-swarm and ralph-wiggum implementations

Example Files

Working examples in examples/:

read-settings-hook.sh - Hook that reads and uses settings
create-settings-command.md - Command that creates settings file
example-settings.md - Template settings file

Utility Scripts

Development tools in scripts/:

validate-settings.sh - Validate settings file structure
parse-frontmatter.sh - Extract frontmatter fields

Implementation Workflow

To add settings to a plugin:

Design settings schema (which fields, types, defaults)
Create template file in plugin documentation
Add gitignore entry for .claude/*.local.md
Implement settings parsing in hooks/commands
Use quick-exit pattern (check file exists, check enabled field)
Document settings in plugin README with template
Remind users that changes require Claude Code restart

Focus on keeping settings simple and providing good defaults when settings file doesn't exist.

Weekly Installs

Repository

davila7/claude-…emplates

GitHub Stars

22.6K

First Seen

Jan 1, 1970

Security Audits

Gen Agent Trust HubFail SocketPass SnykPass

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

144,300 周安装

Claude Code 插件设置配置教程 - YAML Frontmatter 与 Markdown 状态管理

🇨🇳中文介绍

Claude Code 插件的设置模式

概述

文件结构

基本模板

示例：插件状态文件

相关 Skills

读取设置文件

从钩子中读取（Bash 脚本）

从命令中读取

从代理中读取

解析技术

提取 Frontmatter

读取单个字段

读取 Markdown 正文

常见模式

模式 1：临时活动钩子

模式 2：代理状态管理

模式 3：配置驱动行为

创建设置文件

从命令创建

模板生成

最佳实践

文件命名

Gitignore

默认值

验证

重启要求

安全考虑

清理用户输入

验证文件路径

权限

实际示例

multi-agent-swarm 插件

ralph-wiggum 插件

快速参考

文件位置

Frontmatter 解析

正文解析

快速退出模式

附加资源

参考文件

示例文件

实用脚本

实现工作流程

🇺🇸English

Plugin Settings Pattern for Claude Code Plugins

Overview

File Structure

Basic Template

Example: Plugin State File

Reading Settings Files

From Hooks (Bash Scripts)

From Commands

From Agents

Parsing Techniques

Extract Frontmatter

Read Individual Fields

Read Markdown Body

Common Patterns

Pattern 1: Temporarily Active Hooks

Pattern 2: Agent State Management

Pattern 3: Configuration-Driven Behavior

Creating Settings Files

From Commands

Template Generation

Best Practices

File Naming

Gitignore

Defaults

Validation

Restart Requirement

Security Considerations

Sanitize User Input

Validate File Paths

Permissions

Real-World Examples

multi-agent-swarm Plugin

ralph-wiggum Plugin