AgentHub DAG and Branch Status
Get an evidence-backed AgentHub checkpoint showing agent progress, dependency blockers, and verified branch state.
Before & after
Same prompt, same agent — the only difference is the skill.
I can help you check on your agent status. To give you the most accurate picture, could you tell me which agents you're monitoring and what metrics matter most? Are you looking at agent progress, execution time, error rates, or something else? I'd be happy to analyze the data once you share more details about what you're trying to track.
AGENT STATUS REPORT → EXECUTION FLOW Main DAG • 3 stages • 24 nodes active Branch: feat/async-retry • 5 nodes pending Branch: hotfix/logging • 2 nodes passed → AGENT PROGRESS DataProcessor • 87% complete • 12m 34s elapsed ValidationAgent • blocked on input (waiting 2m 18s) ReportGenerator • queued • 5 ahead in line → RECENT MILESTONES ✓ Stage 1 passed (error_count: 0) ✓ 14,200 records processed ⚠ 8 records flagged for manual review ! ValidationAgent timeout risk in 14 minutes → NEXT STEPS 1. Review 8 flagged records now (trap: don't skip review) 2. Consider increasing timeout for ValidationAgent from 20m to 30m 3. Monitor DataProcessor final stage output quality
About this skill
“How are the agents doing?” should get you more than a list of running labels. Get a compact AgentHub checkpoint that explains what finished, what is actually progressing, and exactly why downstream work has not started.
What it does
- Orders DAG nodes by dependency depth so upstream problems appear before their consequences.
- Separates ready work, dependency waits, failures, and states that cannot currently be verified.
- Checks completion claims against the expected artifact or branch output for the current attempt.
- Reports branch existence, worktree changes, and ancestry against the session's recorded base.
- Distinguishes an old progress update from evidence that an agent has stalled.
- Traces blocked work to the actionable upstream cause and identifies the next useful check.
What you get
A concise, timestamped status snapshot with reconciled node counts, concrete blocker paths, branch evidence, and any discrepancies. Ask for one agent, a comparison with the previous checkpoint, or an expanded view of the whole DAG.
Best for
Developers running AgentHub sessions who need to decide whether to wait, investigate an agent, or inspect a branch before merging.
SKILL.md preview
---
name: agenthub-dag-and-branch-status
description: Reports an AgentHub session's current DAG, agent progress, and branch state by reconciling session records with dependency, artifact, and Git evidence. Use when the user says "/hub:status", "how are the agents doing?", "show the DAG status", "why hasn't the downstream agent started?", "my agents keep waiting on each other", "is that agent actually finished?", or "which agent branches exist?".
---
# AgentHub DAG and Branch Status
… (sign up to view the full skill)More development skills
View all Development skills →Performance Bottleneck Profiling: Node, Python, Go
Classifies a slowdown, gives exact profiler commands, reads the output, and proves the fix with same-conditions p95/p99 numbers.
Feature Scaffolding with Working Tests
Turn a short feature spec into code, runnable tests, and integration wiring that match your existing project.
Feature Flag Rollouts and Kill Switches
Design staged flag rollouts, verify rollback paths, and audit flag debt with explicit defaults, gates, and retirement plans.
Microcontroller Firmware and RTOS Engineering
Build and debug MCU firmware with bounded ISR/RTOS timing, safe DMA ownership, and measured power budgets.