Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.
Install with Tessl CLI
npx tessl i github:jdrhyne/agent-skills --skill task-orchestrator83
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Task manifest structure and dependency planning
Manifest top-level fields
12%
100%
Model value
0%
100%
modelTier value
0%
100%
Task status field
0%
100%
Task required fields
25%
100%
Same-file sequential rule
100%
100%
Different-file parallel rule
100%
100%
Phase gate structure
100%
100%
Working directory naming
0%
37%
Issue fetch command
100%
100%
Socket field in manifest
0%
0%
Phases named
25%
100%
Without context: $0.2813 · 1m 1s · 12 turns · 54 in / 4,355 out tokens
With context: $0.3985 · 1m 23s · 17 turns · 344 in / 5,270 out tokens
Heartbeat monitoring and self-healing
Tmux socket flag
0%
100%
Stall threshold value
0%
100%
Completion pattern detection
30%
100%
Input-wait self-heal
70%
100%
Error self-heal with log capture
0%
100%
Unpushed commit detection
100%
100%
Orchestrator pushes externally
100%
100%
Cron schedule value
0%
100%
Capture-pane range
0%
100%
Manifest update
100%
100%
Without context: $0.5166 · 2m 18s · 14 turns · 14 in / 10,565 out tokens
With context: $0.4890 · 1m 57s · 17 turns · 16 in / 7,458 out tokens
Orchestration launch configuration
Config.toml for model
0%
100%
Codex --yolo flag
0%
100%
Worktree branch naming
80%
100%
Tmux socket path
0%
100%
Atomic commit instruction
0%
0%
Push early instruction
0%
0%
PR title format
12%
0%
PR body closes issue
0%
0%
Cleanup kills tmux server
0%
100%
Cleanup removes worktrees
100%
100%
Cleanup removes workdir
100%
100%
Issue number in Codex prompt
100%
100%
Without context: $0.3828 · 1m 40s · 13 turns · 13 in / 7,216 out tokens
With context: $0.4388 · 1m 25s · 16 turns · 17 in / 5,463 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.