
from agent-harness8
Provides a command-driven framework for planning sprints, running coding sessions, and orchestrating parallel subagent work for long-running projects.
Agent Harness organizes multi-session development workflows: sprint planning, single-feature coding sessions, and parallel subagent orchestration. The skill documents slash-command routing and scripts to initialize projects, track features, and archive sprints so the agent can manage project state across sessions and automate routine project-maintenance tasks.
Use when a user requests help breaking requirements into features, running sprint planning, starting a coding session that follows a one-feature-per-session protocol, or executing parallel work with subagents (the 996 pattern). Trigger phrases include: "sprint planning", "init project", "start coding session", "parallel subagents".
Best for agents that orchestrate multi-step workflows and interact with repositories and shells (Claude Code and other coding-focused agents). It is a governance/coordination skill rather than a UI component.
Agent Harness is a multi-session project management framework for AI agents, providing sprint planning, coding sessions, and parallel orchestration via subcommands. Scripts are well-structured Python with argparse; only archive_sprint.py ran cleanly (no data to process), others correctly failed on missing arguments or missing project files. The release.py script uses shell=True in subprocess calls which is a minor security concern but acceptable for a CLI tool with user-supplied arguments.
Well-designed project management skill. Clean separation of concerns with scripts/ and references/. The 996 parallel orchestration feature is unique and practical. No security concerns beyond shell=True in release.py. Scripts gracefully handle missing data states.