From tac
Tracks agentic coding KPIs like streaks, attempts, presence, plan/diff sizes using git diffs and workflow data to assess ZTE readiness and workflow effectiveness.
npx claudepluginhub melodic-software/claude-code-plugins --plugin tacThis skill is limited to using the following tools:
Guide measurement and tracking of agentic coding KPIs to assess ZTE readiness.
Updates agentic coding KPI tables with attempts, plan size, git diff stats after ADW workflows; recalculates streaks and averages for ZTE tracking.
Implements habit tracking for AI agent operations to measure behaviors like test runs, linting, doc updates; detects regressions and visualizes trends for CI/CD and code quality monitoring.
Collects agent usage metrics from git history and generates health reports or dashboards. Use for measuring adoption rates, system health, or periodic reviews via Python script.
Share bugs, ideas, or general feedback.
Guide measurement and tracking of agentic coding KPIs to assess ZTE readiness.
| Metric | Calculation | Target |
|---|---|---|
| Current Streak | Consecutive successes (Attempts <= 2) | Higher is better |
| Longest Streak | Best consecutive success run | Track improvement |
| Average Presence | Mean attempts across all runs | Target: 1 |
| Total Plan Size | Sum of all plan sizes | Track scaling |
| Total Diff Size | Sum of all changes (added + removed) | Track throughput |
| Metric | Source | Meaning |
|---|---|---|
| Attempts | Count of plan/patch runs | 1 = perfect, higher = retries |
| Plan Size | Lines in plan file | Task complexity |
| Diff Size | Lines added + removed | Change magnitude |
| Files Changed | Number of files modified | Change scope |
Only count workflow restarts:
attempts_incrementing = ["adw_plan_iso", "adw_patch_iso"]
attempts = count(workflow in all_adws if workflow in attempts_incrementing)
Build/test/review don't increment - only full replans.
current_streak = 0
for run in reversed(runs):
if run.attempts <= 2:
current_streak += 1
else:
break
git diff origin/main --shortstat
# Output: X files changed, Y insertions(+), Z deletions(-)
Store in app_docs/agentic_kpis.md or equivalent:
# Agentic KPIs
## Summary
| Metric | Value |
| --- | --- |
| Current Streak | 5 |
| Longest Streak | 12 |
| Average Presence | 1.3 |
| Total Plan Size | 450 lines |
| Total Diff Size | 2,340 lines |
## Detail
| Date | ADW ID | Issue | Class | Attempts | Plan Size | Diff +/- | Files |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 2024-01-15 | abc123 | #45 | /bug | 1 | 35 | +45/-12 | 3 |
| 2024-01-14 | def456 | #44 | /feature | 2 | 85 | +120/-30 | 8 |
From state or git:
attempts = count_attempts(all_adws)
plan_size = wc_lines(plan_file)
diff_stats = parse_git_diff()
Add new row with current run data.
Update all summary metrics based on full detail table.
Based on KPIs, assess ZTE readiness:
| Indicator | Threshold | Status |
|---|---|---|
| Current Streak | >= 5 | Ready to try ZTE |
| Average Presence | <= 1.5 | Good efficiency |
| Recent Failures | 0 in last 10 | High confidence |
| Plan Size Trend | Increasing | Scaling up |
Provide KPI update:
## KPI Update
**Run:** {adw_id}
**Issue:** #{issue_number} ({issue_class})
### This Run
- Attempts: 1
- Plan Size: 45 lines
- Diff: +67/-23 (4 files)
### Updated Summary
- Current Streak: 6 (was 5)
- Longest Streak: 12 (unchanged)
- Average Presence: 1.28 (improved)
### Analysis
[Trend observations and recommendations]
Date: 2025-12-26 Model: claude-opus-4-5-20251101