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/run.md

View on GitHub
# Sub-Skill: Execute Workflow

**Parent:** agenthub
**Trigger:** "run workflow", "execute the agents", "start orchestration"

## Purpose

Execute a validated workflow definition end-to-end. Manages the execution lifecycle including agent spawning, dependency resolution, output passing, and final merge.

## Workflow

### Step 1: Load and Validate

Load the workflow definition and run a final validation pass. Ensure all dependencies are satisfiable and configurations are complete.

### Step 2: Initialize Session

Create an orchestration session using `session_manager.py`:
```bash
python scripts/session_manager.py create --workflow workflow.json
```

This creates a session record tracking:
- Session ID and start time
- Agent states (all start as PENDING)
- Output storage locations
- Execution log

### Step 3: Execute Topological Order

Process agents in dependency order:
1. Identify all READY agents (dependencies met)
2. Spawn up to `max_parallel` agents simultaneously
3. Monitor running agents for completion or timeout
4. On completion: store output, update state, check dependents
5. On failure: retry if configured, or mark FAILED and SKIP dependents

### Step 4: Pass Outputs

When an agent completes:
- Validate output format matches the declared schema
- Store output in session state
- Check if any PENDING agents now have all dependencies met
- Transition those agents to READY

### Step 5: Final Merge

When all terminal agents complete:
- Collect their outputs
- Invoke the merge sub-skill (or merge agent if defined)
- Produce the final combined result

### Step 6: Report

Generate an execution report:
- Total wall-clock time
- Per-agent execution times
- Parallelization efficiency
- Quality scores if eval was run
- Any failures or retries

## Inputs

| Input | Required | Description |
|-------|----------|-------------|
| Workflow file | Yes | Path to validated workflow JSON |
| Input data | Yes | Initial inputs for root agents |
| Dry run | No | Simulate without actually executing |

## Outputs

- Final merged result
- Per-agent outputs
- Execution report with timing and quality metrics
- Session record for audit trail
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 CodeCodexVerifiedInstall
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