planner-reflect

Name: planner-reflect
Availability: InStock
Author: spumer

Extract lessons from planning executions and update planner-context.md.

10|1|Updated Feb 6, 2026

Search Tags:#planning #retrospective #ai-agent #lessons-learned #planning-loop #planner-context

Ready to run

npx skills add https://github.com/spumer/i-m-senior-developer --skill planner-reflect

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: planner-reflect
Source: https://github.com/spumer/i-m-senior-developer/tree/main/plugins/planner/skills/planner-reflect
Command: npx skills add https://github.com/spumer/i-m-senior-developer --skill planner-reflect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill closes the planning gap by comparing planned outcomes with actual results and writes actionable lessons into <project-root>/.claude/planner-context.md to improve future planning sessions.

Core Features & Use Cases

Compares plan vs. reality using five evidence sources and updates the planner-context.md with four learning types: gap-fill, model-strength signals, user-correction patterns, and cost-calibration deltas.
Always emits a "Lessons learned" section to ensure retrospective visibility, even when no new lessons are found.
Supports cross-session retrospectives by guiding the update of the planner context for subsequent planning cycles.

Quick Start

Run /plan-reflect after a session that produced PLANNER_OUTPUT.md to generate a lessons report and update planner-context.md.

Frequently Asked Questions about planner-reflect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract lessons learned from a planning execution to improve future AI agent workflows?▼

To extract lessons learned from a planning execution, compare planned outcomes with actual results using multiple evidence sources. This updates your planner context with gap-fill, model-strength signals, user-correction patterns, and cost-calibration deltas to improve future AI agent workflows.

What is a planning loop retrospective and how does it align plans with reality?▼

A planning loop retrospective aligns plans with reality by comparing planned outcomes against actual session results. It extracts actionable insights from five evidence sources and writes them into planner-context.md to continuously calibrate and improve subsequent planning sessions.

How do I update planner-context.md after running a plan-do or plan-reflect session?▼

You update planner-context.md by running a retrospective process after a session that produced PLANNER_OUTPUT.md. The system reads evidence sources, extracts four learning types, and automatically writes the actionable lessons into the file for future reference.

Do I need a PLANNER_OUTPUT.md file to run a retrospective on my project workflow?▼

Yes, you need a PLANNER_OUTPUT.md file to run a retrospective. The process specifically applies to Claude-driven project workflows where this file exists, serving as the baseline to compare against actual execution results and generate lessons learned.

What happens when a planning retrospective finds no new lessons learned?▼

When a planning retrospective finds no new lessons learned, the system always emits a designated "Lessons learned" block anyway. This ensures retrospective visibility is maintained across sessions, confirming the evidence sources were reviewed even if no actionable insights were extracted.

Can I use planning context updates for cross-session project retrospectives?▼

Yes, you can use planning context updates for cross-session project retrospectives. The process guides the update of planner-context.md with historical learning types, ensuring that insights from previous planning loops inform and calibrate subsequent planning cycles.