From harness
Use this skill when the user starts a new session, asks for a status check before beginning work, or wants to verify the environment is ready. Do NOT load for: mid-session implementation work, code reviews, or ongoing task execution. Initializes a work session with environment checks, Plans.md status overview, and readiness verification.
npx claudepluginhub tim-hub/powerball-harness --plugin harnessThis skill is limited to using the following tools:
A skill for verifying the environment and understanding the current task status at session start.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
A skill for verifying the environment and understanding the current task status at session start.
This skill is triggered by the following phrases:
The Session Init skill automatically checks the following at Claude Code session start:
Check file sizes before starting the session:
# Check Plans.md line count
if [ -f "Plans.md" ]; then
lines=$(wc -l < Plans.md)
if [ "$lines" -gt 200 ]; then
echo "⚠️ Plans.md has ${lines} lines. Recommend cleanup with 'clean up'"
fi
fi
# Check session-log.md line count
if [ -f ".claude/memory/session-log.md" ]; then
lines=$(wc -l < .claude/memory/session-log.md)
if [ "$lines" -gt 500 ]; then
echo "⚠️ session-log.md has ${lines} lines. Recommend cleanup with 'clean up session log'"
fi
fi
If cleanup is needed, a suggestion is displayed (does not affect work).
The current standard is the Unified Harness Memory in Step 0.7. Checking legacy local memory compatibility is generally unnecessary; refer to it only when special migration verification is needed.
Note: In normal operation, skip this step and treat the shared DB Resume Pack as the sole resumption path.
Retrieve resume context from the Codex / Claude / OpenCode shared DB (~/.harness-mem/harness-mem.db).
Required call:
harness_mem_resume_pack(project, session_id?, limit=5, include_private=false)
Operational rules:
project must always specify the current project namesession_id is obtained from $CLAUDE_SESSION_ID, falling back to .session_id in .claude/state/session.jsonharness_mem_sessions_list(project, limit=1) is limited to read-only (resume confirmation); do not use it for writes via record_checkpoint / finalize_sessionharness_mem_health(), report the failure explicitly, and continuescripts/harness-memd doctor -> scripts/harness-memd cleanup-stale -> scripts/harness-memd startExecute the following in parallel:
# Git status
git status -sb
git log --oneline -3
# Plans.md
cat Plans.md 2>/dev/null || echo "Plans.md not found"
# Key points from AGENTS.md
head -50 AGENTS.md 2>/dev/null || echo "AGENTS.md not found"
Extract the following from Plans.md:
cc:WIP - Tasks continuing from the previous sessionpm:requesting - Newly requested tasks from the PM (compat: cursor:requesting)cc:TODO - Unstarted but assigned tasks## 🚀 Session Start
**Date/Time**: {{YYYY-MM-DD HH:MM}}
**Branch**: {{branch}}
**Session ID**: ${CLAUDE_SESSION_ID}
---
### 📋 Today's Tasks
**Priority Tasks**:
- {{pm:requesting (compat: cursor:requesting) or cc:WIP tasks}}
**Other Tasks**:
- {{List of cc:TODO tasks}}
---
### ⚠️ Notes
{{Important constraints and prohibitions from AGENTS.md}}
---
**Ready to start work?**
At session start, present the following information concisely:
| Item | Content |
|---|---|
| Current branch | e.g., staging |
| Priority tasks | Top 1-2 most important |
| Notes | Summary of prohibitions |
| Next action | Specific suggestions |
/work - Execute tasks (supports parallel execution)/sync-status - Progress summary for Plans.md/maintenance - Auto-cleanup of files/harness-init