gilles/claude-code-best-practice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

allowed agent calling within an agent

Browse Source
This commit is contained in:
Shayan Rais
2025-11-03 20:50:10 +05:00
parent 0b7e7dd440
commit 4d7f1d9e6e
6 changed files with 197 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/commands/weather-karachi.md
+19
View File
@@ -0,0 +1,19 @@
---
description: Fetch and transform weather data for Karachi
model: haiku
---
# Weather Karachi Command
Fetch the current temperature for Karachi, Pakistan and apply transformations.
## Workflow
1. Use the weather-fetcher agent to retrieve the current temperature from wttr.in API
2. Use the weather-transformer agent to read transformation rules from input/input.md and apply them to the temperature
3. Write the results to output/output.md
Launch the agents sequentially (not in parallel) and provide a clear summary showing:
- Original temperature
- Transformation applied
- Final result
.claude/commands/weather.md
+3 -13
View File
@@ -1,20 +1,10 @@
---
description: Fetch and transform weather data for a city
argument-hint: <city-name>
description: Fetch and transform weather data for Karachi
model: haiku
---
# Weather Command
Fetch the current temperature for ${1:-Karachi}, Pakistan and apply transformations.
Execute the weather-karachi command to fetch and transform temperature data.
## Workflow
1. Use the weather-fetcher agent to retrieve the current temperature from wttr.in API
2. Use the weather-transformer agent to read transformation rules from input/input.md and apply them to the temperature
3. Write the results to output/output.md
Launch the agents sequentially (not in parallel) and provide a clear summary showing:
- Original temperature
- Transformation applied
- Final result
Use the SlashCommand tool to execute `/weather-karachi`.
docs/AGENTS.md
+1 -1
View File
@@ -101,7 +101,7 @@ After updating the orchestrator agent definition, test it by invoking the orches
```bash
# Via slash command
/weather
/weather-karachi
# Or directly via Task tool
Task(subagent_type="weather-orchestrator", description="Run weather workflow", prompt="Orchestrate the complete weather workflow", model="haiku")
docs/PROMPTS.md
+3 -3
View File
@@ -20,7 +20,7 @@ see the table in @PROMPTS.md of Agent Invocation and Command Invocation and cros
| From | How | Example |
|----------------------|------------------------|-------------------------------------|
| Claude CLI | Prompt | use the weather command to fetch the weather |
| Claude CLI | /command-name | /weather |
| /agents/Agents.md | SlashCommand tool | SlashCommand(command="/weather Karachi") |
| Another /command | SlashCommand tool | SlashCommand(command="/weather Karachi") |
| Claude CLI | /command-name | /weather-karachi |
| /agents/Agents.md | SlashCommand tool | SlashCommand(command="/weather-karachi") |
| Another /command | SlashCommand tool | SlashCommand(command="/weather-karachi") |
docs/WEATHER.md
+167
View File
@@ -0,0 +1,167 @@
# Weather Karachi System Flow
This document describes the complete flow of the weather data fetching and transformation system.
## System Overview
The weather system consists of slash commands and specialized agents that work together to fetch and transform temperature data for Karachi, Pakistan.
## Flow Diagram
```
┌─────────────────────────────────────────────────────────────────┐
│ User Interaction │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌──────────────────┐
│ /weather │
│ Command │
└──────────────────┘
│
│ calls
▼
┌──────────────────┐
│ /weather-karachi │
│ Command │
└──────────────────┘
│
│ Step 1 (Sequential)
▼
┌────────────────────────┐
│ weather-fetcher │
│ Agent │
│ (subagent_type) │
└────────────────────────┘
│
▼
┌────────────────────────┐
│ wttr.in API │
│ Fetch Temperature │
│ for Karachi │
└────────────────────────┘
│
│ Returns: 26°C
▼
│
│ Step 2 (Sequential)
▼
┌─────────────────────────┐
│ weather-transformer │
│ Agent │
│ (subagent_type) │
└─────────────────────────┘
│
▼
┌─────────────────────────┐
│ input/input.md │
│ Read Transform Rules │
└─────────────────────────┘
│
│ Reads: "add +10"
▼
┌────────────────────────┐
│ Apply Transform │
│ 26 + 10 = 36°C │
└────────────────────────┘
│
▼
┌────────────────────────┐
│ output/output.md │
│ Write Results │
└────────────────────────┘
│
▼
┌────────────────────────┐
│ Display Summary │
│ to User │
└────────────────────────┘
```
## Component Details
### 1. Slash Commands
#### `/weather`
- **Location**: `.claude/commands/weather.md`
- **Purpose**: Entry point for weather operations
- **Action**: Calls `/weather-karachi` command
- **Model**: haiku
#### `/weather-karachi`
- **Location**: `.claude/commands/weather-karachi.md`
- **Purpose**: Orchestrates the weather fetching and transformation workflow
- **Action**: Launches two specialized agents sequentially
- **Model**: haiku
### 2. Specialized Agents
#### `weather-fetcher`
- **Location**: `.claude/agents/weather-fetcher.md`
- **Purpose**: Fetch real-time temperature data
- **Data Source**: wttr.in API for Karachi, Pakistan
- **Output**: Temperature in Celsius (numeric value)
- **Tools Available**: WebFetch
#### `weather-transformer`
- **Location**: `.claude/agents/weather-transformer.md`
- **Purpose**: Apply mathematical transformations to temperature data
- **Input Source**: `input/input.md` (transformation rules)
- **Output Destination**: `output/output.md` (formatted results)
- **Tools Available**: Read, Write
### 3. Data Files
#### `input/input.md`
- **Purpose**: Stores transformation rules
- **Format**: Natural language instructions (e.g., "add +10 in the result")
- **Access**: Read by weather-transformer agent
#### `output/output.md`
- **Purpose**: Stores formatted transformation results
- **Format**: Structured markdown with sections:
- Original Temperature
- Transformation Applied
- Final Result
- Calculation Details
## Execution Flow
1. **User Invocation**: User runs `/weather` command
2. **Command Delegation**: `/weather` delegates to `/weather-karachi`
3. **Sequential Agent Execution**:
- **Step 1**: `weather-fetcher` agent fetches current temperature from wttr.in
- **Step 2**: `weather-transformer` agent:
- Reads transformation rules from `input/input.md`
- Applies rules to the fetched temperature
- Formats and writes results to `output/output.md`
4. **Result Display**: Summary shown to user with:
- Original temperature
- Transformation rule applied
- Final transformed result
## Example Execution
```
Input: /weather
├─ Calls: /weather-karachi
│ ├─ Agent: weather-fetcher
│ │ └─ Result: 26°C
│ ├─ Agent: weather-transformer
│ │ ├─ Reads: input/input.md ("add +10")
│ │ ├─ Calculates: 26 + 10 = 36°C
│ │ └─ Writes: output/output.md
│ └─ Output:
│ ├─ Original: 26°C
│ ├─ Transform: Add +10
│ └─ Result: 36°C
```
## Key Design Principles
1. **Separation of Concerns**: Each component has a single, clear responsibility
2. **Sequential Execution**: Agents run in order to ensure data dependencies are met
3. **Specialized Agents**: Task-specific agents with minimal tool access
4. **Command Chaining**: Simple commands can delegate to more complex workflows
5. **Configurable Transformations**: Rules stored externally in input files
6. **Structured Output**: Results formatted consistently in output files
output/output.md
+4 -4
View File
@@ -1,13 +1,13 @@
# Weather Transformation Results
**Original Temperature:** 50°C
**Original Temperature:** 26°C
**Transformation Applied:** Add +10 to the result
**Final Result:** 60°C
**Final Result:** 36°C
## Calculation Details
- Starting value: 50°C
- Starting value: 26°C
- Operation: +10
- Result: 50 + 10 = 60°C
- Result: 26 + 10 = 36°C