Skip to content

borghei/Claude-Skills / engineering/agenthub

agenthub

Verified

Runs a multi-agent job as a dependency graph: validates the DAG, tracks each agent's state on a board, then ranks and merges their outputs. Use when spawning parallel agents, monitoring a run, or merging results.

FileKindSize
SKILL.mdskill md9.8 KB
assets/sample_session.jsonconfig4.5 KB
assets/sample_workflow.jsonconfig1.5 KB
references/multi-agent-patterns.mdmarkdown5.6 KB
references/operations-and-quality.mdmarkdown2.9 KB
references/orchestration-core.mdmarkdown4.9 KB
scripts/board_manager.pyscript10.9 KB
scripts/dag_analyzer.pyscript13.5 KB
scripts/result_ranker.pyscript11.0 KB
scripts/session_manager.pyscript12.7 KB
skills/board.mdmarkdown2.2 KB
skills/eval.mdmarkdown2.2 KB
skills/init.mdmarkdown2.0 KB
skills/merge.mdmarkdown2.3 KB
skills/run.mdmarkdown2.1 KB
skills/spawn.mdmarkdown1.9 KB
skills/status.mdmarkdown2.1 KB

skills/spawn.md

View on GitHub
# Sub-Skill: Spawn Agent

**Parent:** agenthub
**Trigger:** "spawn agent", "create agent instance", "start sub-agent"

## Purpose

Spawn an individual agent within a workflow. Prepares the agent's context, passes inputs from upstream agents, monitors execution, and captures outputs.

## Workflow

### Step 1: Prepare Context

Assemble the agent's execution context:
- Task description from the workflow definition
- Input data from upstream agent outputs
- Constraints: timeout, output format, quality expectations
- Relevant reference material (if specified)

### Step 2: Configure Agent

Set agent parameters:
```
Agent ID:       researcher-001
Task:           Research competitor landscape
Inputs:         { product_description: "..." }
Expected output: { competitor_list: [], market_size: {} }
Timeout:        300s
Retries:        1
```

### Step 3: Execute

Launch the agent and monitor:
- Start the agent with prepared context
- Track execution time
- Capture stdout/output as it streams
- Watch for timeout

### Step 4: Capture Output

On completion:
- Parse agent output into structured format
- Validate output matches expected schema
- Store in session state keyed by agent ID
- Transition state to COMPLETED

On failure:
- Capture error message and stack trace
- If retries remain, re-spawn with error context
- If no retries, transition to FAILED

### Step 5: Notify Orchestrator

Report back to the workflow engine:
- Agent state transition
- Output availability
- Duration and resource usage
- Quality signals (if evaluatable)

## Inputs

| Input | Required | Description |
|-------|----------|-------------|
| Agent definition | Yes | From workflow definition |
| Upstream outputs | Yes | Data from completed dependencies |
| Session ID | Yes | Orchestration session reference |

## Outputs

- Agent output in structured format
- Execution metadata (duration, retries, state)
- Error details (if failed)
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall