Open-source plugin estimates Claude Code task duration based on local measurements
Understand this story
Noam Brand released the open-source plugin AI Time Estimator, which lets Claude Code estimate task duration in its own working minutes rather than human-experience guesses like "2–3 days." The plugin uses subagents to count file reads and writes, command executions, and other operations, then estimate.py runs a Monte Carlo simulation using locally measured rates to output P10/P50/P90 time ranges. Use requires Python 3.9+ in the local PATH, with no pip installation needed. The first session measures rates in the background for about a minute, after which each answer is automatically scored and corrected; after 10 ratings, the ranges are adjusted based on the user's own results, and each answer includes a history record. Brand says all data stays local, and the plugin makes no network requests and sends nothing externally.
AI overview based on source reports · Updated 54 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: AI Time Estimator – how long Claude Code will take, from your own logs
AI Time Estimator is a Claude Code plugin that has a subagent count the operations a task needs and converts those counts into P10/P50/P90 minutes via Monte Carlo simulation, using rates measured from the user's own Claude Code transcripts. A Stop hook scores each estimate against what actually happened, and after 10 scored estimates the ranges self-correct; everything runs locally with no network calls. It requires Python 3.9+ and installs as a plugin or via install.py, which adds an agent, an /estimate-here command, a hook and a CLAUDE.md section.
Activity for this story
Not enough continuous observations to show a trend yet.