issue-tracking

SkillMonitoring & ops

Lets your agent track issues in git-backed storage and monitor their progress over time.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the issue-tracking skill

About this capability

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/gastown/skills/issue-tracking/SKILL.md and read by ahel’s review.

  • Tracking bead progress and status
  • Managing bead dependencies
  • Collecting attribution data for agent evaluation

Bead Lifecycle

  1. Created: Bead defined with scope and acceptance criteria
  2. Assigned: Bead placed on agent's hook
  3. In Progress: Agent actively working (GUPP enforced)
  4. Review: Work complete, awaiting merge review
  5. Done: Merged and verified (gt done)
  6. Destroyed: Wisps only - cleaned up after landing

Attribution

All work carries persistent attribution:

  • Which agent completed the bead
  • Time taken and quality score
  • Used for A/B testing agent configurations
  • Feeds into agent evaluation and scoring

Tool Use

Used within convoy management and orchestrator processes.

Signals

GitHub stars
2k
Forks
106
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
issue-tracking
Source
github.com/a5c-ai/babysitter