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/status.md

View on GitHub
# Sub-Skill: Workflow Status

**Parent:** agenthub
**Trigger:** "workflow status", "orchestration health", "how is the run going"

## Purpose

Report the overall status and health of a workflow execution. Provides a compact summary of progress, timing, failures, and estimated completion.

## Workflow

### Step 1: Load Session

```bash
python scripts/session_manager.py status --session <session-id>
```

### Step 2: Compute Metrics

| Metric | Calculation |
|--------|-------------|
| Progress | completed_agents / total_agents * 100% |
| Elapsed time | now - session_start |
| Est. remaining | critical_path_remaining * avg_agent_duration |
| Parallelization | time_agents_ran_parallel / total_agent_time |
| Failure rate | failed_agents / attempted_agents |
| Quality avg | mean(eval_scores) for completed agents |

### Step 3: Determine Health

| Condition | Health Status |
|-----------|--------------|
| All agents on track, no failures | HEALTHY |
| Minor delays but progressing | DEGRADED |
| Agent failed, retrying | AT_RISK |
| Multiple failures, blocked | CRITICAL |
| All agents complete | COMPLETE |

### Step 4: Display Status

```
Workflow Status: market-analysis
Session: abc123
Health: HEALTHY

Progress: ████████░░░░░░░░ 50% (2/4 agents)
Elapsed:  3m 15s
Est. remaining: 4m 00s

Agents:
  researcher      COMPLETED  1m 30s
  data_collector  COMPLETED  1m 45s
  analyst         RUNNING    0m 30s...
  writer          PENDING    (waiting: analyst)

Quality: 0.85 avg (2 evaluated)
Failures: 0
Retries: 0
```

### Step 5: Recommendations

If health is not HEALTHY:
- Suggest timeout adjustments
- Identify bottleneck agents
- Recommend retry or skip strategies

## Inputs

| Input | Required | Description |
|-------|----------|-------------|
| Session ID | Yes | Active orchestration session |
| Verbose | No | Show per-agent details (default: summary) |

## Outputs

- Health status with color indicator
- Progress percentage and agent counts
- Timing breakdown (elapsed, estimated remaining)
- Quality metrics
- Actionable recommendations (if issues detected)
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