planning-with-files 3.9.0

package/scripts/set-active-plan.ps1

@@ -0,0 +1,51 @@
+# planning-with-files: set or display the active plan pointer (PowerShell).
+#
+# Usage:
+#   .\set-active-plan.ps1 <plan_id>   - pin .planning\.active_plan to plan_id
+#   .\set-active-plan.ps1             - print the current active plan (if any)
+
+param(
+    [string]$PlanId = ""
+)
+
+$PlanRoot  = Join-Path (Get-Location) ".planning"
+$ActiveFile = Join-Path $PlanRoot ".active_plan"
+
+if ($PlanId -eq "") {
+    if (Test-Path $ActiveFile) {
+        $current = (Get-Content $ActiveFile -Raw -Encoding UTF8).Trim()
+        $planDir = Join-Path $PlanRoot $current
+        if ($current -ne "" -and (Test-Path $planDir)) {
+            Write-Output "Active plan: $current"
+            Write-Output "Path: $planDir"
+        } elseif ($current -ne "") {
+            Write-Output "Active plan pointer: $current (directory not found - stale pointer)"
+        } else {
+            Write-Output "No active plan set."
+        }
+    } else {
+        Write-Output "No active plan set."
+    }
+    exit 0
+}
+
+$PlanDir = Join-Path $PlanRoot $PlanId
+
+if (-not (Test-Path $PlanDir)) {
+    Write-Error "Error: plan directory not found: $PlanDir"
+    Write-Error "Run: init-session.sh `"$PlanId`" to create it, or check .planning\ for available plans."
+    exit 1
+}
+
+if (-not (Test-Path $PlanRoot)) {
+    New-Item -ItemType Directory -Path $PlanRoot -Force | Out-Null
+}
+
+$utf8NoBom = New-Object System.Text.UTF8Encoding($false)
+[System.IO.File]::WriteAllText($ActiveFile, $PlanId, $utf8NoBom)
+
+Write-Output "Active plan set to: $PlanId"
+Write-Output "Path: $PlanDir"
+Write-Output ""
+Write-Output "To pin this terminal session only:"
+Write-Output "`$env:PLAN_ID = '$PlanId'"

package/scripts/set-active-plan.sh

@@ -0,0 +1,50 @@
+#!/bin/sh
+# planning-with-files: set or display the active plan pointer.
+#
+# Usage:
+#   set-active-plan.sh <plan_id>   — pin .planning/.active_plan to plan_id
+#   set-active-plan.sh             — print the current active plan (if any)
+#
+# The active plan is stored in .planning/.active_plan and is read by
+# resolve-plan-dir.sh when no $PLAN_ID env var is set.
+
+set -e
+
+PLAN_ROOT="${PWD}/.planning"
+ACTIVE_FILE="${PLAN_ROOT}/.active_plan"
+
+# No args → show current active plan
+if [ "${1:-}" = "" ]; then
+    if [ -f "${ACTIVE_FILE}" ]; then
+        plan_id="$(tr -d '\r\n' < "${ACTIVE_FILE}")"
+        if [ -n "${plan_id}" ] && [ -d "${PLAN_ROOT}/${plan_id}" ]; then
+            echo "Active plan: ${plan_id}"
+            echo "Path: ${PLAN_ROOT}/${plan_id}"
+        elif [ -n "${plan_id}" ]; then
+            echo "Active plan pointer: ${plan_id} (directory not found — stale pointer)"
+        else
+            echo "No active plan set."
+        fi
+    else
+        echo "No active plan set."
+    fi
+    exit 0
+fi
+
+PLAN_ID="$1"
+PLAN_DIR="${PLAN_ROOT}/${PLAN_ID}"
+
+if [ ! -d "${PLAN_DIR}" ]; then
+    echo "Error: plan directory not found: ${PLAN_DIR}" >&2
+    echo "Run: init-session.sh \"${PLAN_ID}\" to create it, or check .planning/ for available plans." >&2
+    exit 1
+fi
+
+mkdir -p "${PLAN_ROOT}"
+printf "%s\n" "${PLAN_ID}" > "${ACTIVE_FILE}"
+
+echo "Active plan set to: ${PLAN_ID}"
+echo "Path: ${PLAN_DIR}"
+echo ""
+echo "To pin this terminal session only:"
+echo "  export PLAN_ID=${PLAN_ID}"

package/templates/analytics_findings.md

@@ -0,0 +1,85 @@
+# Findings & Decisions
+<!--
+  WHAT: Knowledge base for your analytics session. Stores data sources, hypotheses, and results.
+  WHY: Context windows are limited. This file is your "external memory" for analytical work.
+  WHEN: Update after ANY discovery, especially after running queries or viewing charts.
+-->
+
+## Data Sources
+<!--
+  WHAT: Every data source you connected to, with schema details and quality notes.
+  WHY: Knowing where your data came from and its limitations is critical for reproducibility.
+  EXAMPLE:
+    | user_events | PostgreSQL prod replica | 2.3M rows | user_id, event_type, ts | 0.2% null user_id |
+    | revenue.csv | Finance team export | 45K rows | account_id, mrr, churn_date | Complete, no nulls |
+-->
+| Source | Location | Size | Key Fields | Quality Notes |
+|--------|----------|------|------------|---------------|
+|        |          |      |            |               |
+
+## Hypothesis Log
+<!--
+  WHAT: Each hypothesis you tested, the method used, and the result.
+  WHY: Structured tracking prevents p-hacking and makes your reasoning auditable.
+  EXAMPLE:
+    | H1: Churn > 50% for low-activity users | Chi-squared test | Confirmed (p=0.003) | High |
+    | H2: Feature X correlates with retention | Pearson correlation | Rejected (r=0.08) | High |
+-->
+| Hypothesis | Test Method | Result | Confidence |
+|------------|-------------|--------|------------|
+|            |             |        |            |
+
+## Query Results
+<!--
+  WHAT: Key queries you ran and what they revealed.
+  WHY: Queries are ephemeral - if you don't write down the results, they're lost on context reset.
+  WHEN: After EVERY significant query. Don't wait.
+  EXAMPLE:
+    ### Churn rate by activity segment
+    Query: SELECT activity_bucket, COUNT(*), AVG(churned) FROM user_segments GROUP BY 1
+    Result: Low activity: 62% churn, Medium: 28%, High: 8%
+    Interpretation: Strong inverse relationship between activity and churn
+-->
+<!-- Record query, result summary, and interpretation for each significant query -->
+
+## Statistical Findings
+<!--
+  WHAT: Formal statistical test results with all relevant metrics.
+  WHY: Recording p-values, effect sizes, and confidence intervals makes results reproducible.
+  EXAMPLE:
+    | Chi-squared (churn ~ activity) | p=0.003 | Cramer's V=0.31 | Reject null: activity segments differ significantly in churn |
+    | Pearson (feature_x ~ retention) | p=0.42 | r=0.08 | Fail to reject: no meaningful correlation |
+-->
+| Test | p-value | Effect Size | Conclusion |
+|------|---------|-------------|------------|
+|      |         |             |            |
+
+## Technical Decisions
+<!--
+  WHAT: Analytical method choices with reasoning.
+  EXAMPLE:
+    | Use log transform on revenue | Right-skewed distribution, normalizes for parametric tests |
+-->
+| Decision | Rationale |
+|----------|-----------|
+|          |           |
+
+## Issues Encountered
+| Issue | Resolution |
+|-------|------------|
+|       |            |
+
+## Resources
+<!-- URLs, file paths, documentation links -->
+-
+
+## Visual/Browser Findings
+<!--
+  CRITICAL: Update after viewing charts, dashboards, or browser results.
+  Multimodal content doesn't persist in context - capture as text immediately.
+-->
+-
+
+---
+*Update this file after every 2 view/browser/search operations*
+*This prevents visual information from being lost*

package/templates/analytics_task_plan.md

@@ -0,0 +1,106 @@
+# Task Plan: [Analytics Project Description]
+<!--
+  WHAT: Roadmap for a data analytics or exploration session.
+  WHY: Analytics workflows have different phases than software development — hypothesis testing,
+       data quality checks, and statistical validation don't map to a generic build cycle.
+  WHEN: Create this FIRST before starting any data exploration. Update after each phase.
+-->
+
+## Goal
+<!--
+  WHAT: One clear sentence describing what you're trying to learn or produce.
+  EXAMPLE: "Determine which user segments have the highest churn risk using last 90 days of activity data."
+-->
+[One sentence describing the analytical objective]
+
+## Current Phase
+<!--
+  WHAT: Which phase you're currently working on (e.g., "Phase 1", "Phase 3").
+  WHY: Quick reference for where you are. Update this as you progress.
+-->
+Phase 1
+
+## Phases
+
+### Phase 1: Data Discovery
+<!--
+  WHAT: Connect to data sources, understand schemas, assess data quality.
+  WHY: Bad data produces bad analysis. This phase prevents wasted effort on unreliable inputs.
+-->
+- [ ] Identify and connect to data sources
+- [ ] Document schemas and field descriptions in findings.md
+- [ ] Assess data quality (nulls, duplicates, outliers, date ranges)
+- [ ] Estimate dataset size and query performance
+- **Status:** in_progress
+
+### Phase 2: Exploratory Analysis
+<!--
+  WHAT: Distributions, correlations, outliers, initial patterns.
+  WHY: Understanding the shape of your data before testing hypotheses prevents false conclusions.
+-->
+- [ ] Compute summary statistics for key variables
+- [ ] Visualize distributions and relationships
+- [ ] Identify outliers and anomalies
+- [ ] Document initial patterns in findings.md
+- **Status:** pending
+
+### Phase 3: Hypothesis Testing
+<!--
+  WHAT: Formalize hypotheses, run statistical tests, validate findings.
+  WHY: Moving from "it looks like X" to "we can confidently say X" requires structured testing.
+-->
+- [ ] Formalize hypotheses from exploratory phase
+- [ ] Select appropriate statistical tests
+- [ ] Run tests and record results in findings.md
+- [ ] Validate findings against holdout data or alternative methods
+- **Status:** pending
+
+### Phase 4: Synthesis & Reporting
+<!--
+  WHAT: Summarize findings, create visualizations, document conclusions.
+  WHY: Analysis without clear communication is wasted work. This phase produces the deliverable.
+-->
+- [ ] Summarize key findings with supporting evidence
+- [ ] Create final visualizations
+- [ ] Document conclusions and recommendations
+- [ ] Note limitations and areas for further investigation
+- **Status:** pending
+
+## Hypotheses
+<!--
+  WHAT: Questions you're investigating, stated as testable hypotheses.
+  WHY: Explicit hypotheses prevent fishing expeditions and keep analysis focused.
+  EXAMPLE:
+    1. Users who logged in < 3 times in the last 30 days have > 50% churn rate (H1)
+    2. Feature X adoption correlates with retention (r > 0.3) (H2)
+-->
+1. [Hypothesis to test]
+2. [Hypothesis to test]
+
+## Decisions Made
+<!--
+  WHAT: Analytical decisions with reasoning (e.g., choosing a test, filtering criteria).
+  EXAMPLE:
+    | Use median instead of mean | Revenue data is heavily right-skewed |
+    | Filter to last 90 days | Earlier data uses a different tracking schema |
+-->
+| Decision | Rationale |
+|----------|-----------|
+|          |           |
+
+## Errors Encountered
+<!--
+  WHAT: Every error you encounter, what attempt number it was, and how you resolved it.
+  EXAMPLE:
+    | Query timeout on raw table | 1 | Added date partition filter |
+    | Null join keys in user_events | 2 | Inner join instead of left join, documented data loss |
+-->
+| Error | Attempt | Resolution |
+|-------|---------|------------|
+|       | 1       |            |
+
+## Notes
+- Update phase status as you progress: pending -> in_progress -> complete
+- Re-read this plan before major analytical decisions
+- Log ALL errors - they help avoid repetition
+- Write query results and visual findings to findings.md immediately

package/templates/findings.md

@@ -0,0 +1,95 @@
+# Findings & Decisions
+<!-- 
+  WHAT: Your knowledge base for the task. Stores everything you discover and decide.
+  WHY: Context windows are limited. This file is your "external memory" - persistent and unlimited.
+  WHEN: Update after ANY discovery, especially after 2 view/browser/search operations (2-Action Rule).
+-->
+
+## Requirements
+<!-- 
+  WHAT: What the user asked for, broken down into specific requirements.
+  WHY: Keeps requirements visible so you don't forget what you're building.
+  WHEN: Fill this in during Phase 1 (Requirements & Discovery).
+  EXAMPLE:
+    - Command-line interface
+    - Add tasks
+    - List all tasks
+    - Delete tasks
+    - Python implementation
+-->
+<!-- Captured from user request -->
+-
+
+## Research Findings
+<!-- 
+  WHAT: Key discoveries from web searches, documentation reading, or exploration.
+  WHY: Multimodal content (images, browser results) doesn't persist. Write it down immediately.
+  WHEN: After EVERY 2 view/browser/search operations, update this section (2-Action Rule).
+  EXAMPLE:
+    - Python's argparse module supports subcommands for clean CLI design
+    - JSON module handles file persistence easily
+    - Standard pattern: python script.py <command> [args]
+-->
+<!-- Key discoveries during exploration -->
+-
+
+## Technical Decisions
+<!-- 
+  WHAT: Architecture and implementation choices you've made, with reasoning.
+  WHY: You'll forget why you chose a technology or approach. This table preserves that knowledge.
+  WHEN: Update whenever you make a significant technical choice.
+  EXAMPLE:
+    | Use JSON for storage | Simple, human-readable, built-in Python support |
+    | argparse with subcommands | Clean CLI: python todo.py add "task" |
+-->
+<!-- Decisions made with rationale -->
+| Decision | Rationale |
+|----------|-----------|
+|          |           |
+
+## Issues Encountered
+<!-- 
+  WHAT: Problems you ran into and how you solved them.
+  WHY: Similar to errors in task_plan.md, but focused on broader issues (not just code errors).
+  WHEN: Document when you encounter blockers or unexpected challenges.
+  EXAMPLE:
+    | Empty file causes JSONDecodeError | Added explicit empty file check before json.load() |
+-->
+<!-- Errors and how they were resolved -->
+| Issue | Resolution |
+|-------|------------|
+|       |            |
+
+## Resources
+<!-- 
+  WHAT: URLs, file paths, API references, documentation links you've found useful.
+  WHY: Easy reference for later. Don't lose important links in context.
+  WHEN: Add as you discover useful resources.
+  EXAMPLE:
+    - Python argparse docs: https://docs.python.org/3/library/argparse.html
+    - Project structure: src/main.py, src/utils.py
+-->
+<!-- URLs, file paths, API references -->
+-
+
+## Visual/Browser Findings
+<!-- 
+  WHAT: Information you learned from viewing images, PDFs, or browser results.
+  WHY: CRITICAL - Visual/multimodal content doesn't persist in context. Must be captured as text.
+  WHEN: IMMEDIATELY after viewing images or browser results. Don't wait!
+  EXAMPLE:
+    - Screenshot shows login form has email and password fields
+    - Browser shows API returns JSON with "status" and "data" keys
+-->
+<!-- CRITICAL: Update after every 2 view/browser operations -->
+<!-- Multimodal content must be captured as text immediately -->
+-
+
+---
+<!-- 
+  REMINDER: The 2-Action Rule
+  After every 2 view/browser/search operations, you MUST update this file.
+  This prevents visual information from being lost when context resets.
+-->
+*Update this file after every 2 view/browser/search operations*
+*This prevents visual information from being lost*

package/templates/progress.md

@@ -0,0 +1,114 @@
+# Progress Log
+<!-- 
+  WHAT: Your session log - a chronological record of what you did, when, and what happened.
+  WHY: Answers "What have I done?" in the 5-Question Reboot Test. Helps you resume after breaks.
+  WHEN: Update after completing each phase or encountering errors. More detailed than task_plan.md.
+-->
+
+## Session: [DATE]
+<!-- 
+  WHAT: The date of this work session.
+  WHY: Helps track when work happened, useful for resuming after time gaps.
+  EXAMPLE: 2026-01-15
+-->
+
+### Phase 1: [Title]
+<!-- 
+  WHAT: Detailed log of actions taken during this phase.
+  WHY: Provides context for what was done, making it easier to resume or debug.
+  WHEN: Update as you work through the phase, or at least when you complete it.
+-->
+- **Status:** in_progress
+- **Started:** [timestamp]
+<!-- 
+  STATUS: Same as task_plan.md (pending, in_progress, complete)
+  TIMESTAMP: When you started this phase (e.g., "2026-01-15 10:00")
+-->
+- Actions taken:
+  <!-- 
+    WHAT: List of specific actions you performed.
+    EXAMPLE:
+      - Created todo.py with basic structure
+      - Implemented add functionality
+      - Fixed FileNotFoundError
+  -->
+  -
+- Files created/modified:
+  <!-- 
+    WHAT: Which files you created or changed.
+    WHY: Quick reference for what was touched. Helps with debugging and review.
+    EXAMPLE:
+      - todo.py (created)
+      - todos.json (created by app)
+      - task_plan.md (updated)
+  -->
+  -
+
+### Phase 2: [Title]
+<!-- 
+  WHAT: Same structure as Phase 1, for the next phase.
+  WHY: Keep a separate log entry for each phase to track progress clearly.
+-->
+- **Status:** pending
+- Actions taken:
+  -
+- Files created/modified:
+  -
+
+## Test Results
+<!-- 
+  WHAT: Table of tests you ran, what you expected, what actually happened.
+  WHY: Documents verification of functionality. Helps catch regressions.
+  WHEN: Update as you test features, especially during Phase 4 (Testing & Verification).
+  EXAMPLE:
+    | Add task | python todo.py add "Buy milk" | Task added | Task added successfully | ✓ |
+    | List tasks | python todo.py list | Shows all tasks | Shows all tasks | ✓ |
+-->
+| Test | Input | Expected | Actual | Status |
+|------|-------|----------|--------|--------|
+|      |       |          |        |        |
+
+## Error Log
+<!-- 
+  WHAT: Detailed log of every error encountered, with timestamps and resolution attempts.
+  WHY: More detailed than task_plan.md's error table. Helps you learn from mistakes.
+  WHEN: Add immediately when an error occurs, even if you fix it quickly.
+  EXAMPLE:
+    | 2026-01-15 10:35 | FileNotFoundError | 1 | Added file existence check |
+    | 2026-01-15 10:37 | JSONDecodeError | 2 | Added empty file handling |
+-->
+<!-- Keep ALL errors - they help avoid repetition -->
+| Timestamp | Error | Attempt | Resolution |
+|-----------|-------|---------|------------|
+|           |       | 1       |            |
+
+## 5-Question Reboot Check
+<!-- 
+  WHAT: Five questions that verify your context is solid. If you can answer these, you're on track.
+  WHY: This is the "reboot test" - if you can answer all 5, you can resume work effectively.
+  WHEN: Update periodically, especially when resuming after a break or context reset.
+  
+  THE 5 QUESTIONS:
+  1. Where am I? → Current phase in task_plan.md
+  2. Where am I going? → Remaining phases
+  3. What's the goal? → Goal statement in task_plan.md
+  4. What have I learned? → See findings.md
+  5. What have I done? → See progress.md (this file)
+-->
+<!-- If you can answer these, context is solid -->
+| Question | Answer |
+|----------|--------|
+| Where am I? | Phase X |
+| Where am I going? | Remaining phases |
+| What's the goal? | [goal statement] |
+| What have I learned? | See findings.md |
+| What have I done? | See above |
+
+---
+<!-- 
+  REMINDER: 
+  - Update after completing each phase or encountering errors
+  - Be detailed - this is your "what happened" log
+  - Include timestamps for errors to track when issues occurred
+-->
+*Update after completing each phase or encountering errors*

package/templates/task_plan.md

@@ -0,0 +1,140 @@
+# Task Plan: [Brief Description]
+<!-- 
+  WHAT: This is your roadmap for the entire task. Think of it as your "working memory on disk."
+  WHY: After 50+ tool calls, your original goals can get forgotten. This file keeps them fresh.
+  WHEN: Create this FIRST, before starting any work. Update after each phase completes.
+-->
+
+## Goal
+<!-- 
+  WHAT: One clear sentence describing what you're trying to achieve.
+  WHY: This is your north star. Re-reading this keeps you focused on the end state.
+  EXAMPLE: "Create a Python CLI todo app with add, list, and delete functionality."
+-->
+[One sentence describing the end state]
+
+## Next Step
+<!-- 
+  WHAT: The single next action you are about to take. Keep it to one imperative line.
+  WHY: Sits right after the goal, so every hook injection carries the immediate action.
+  WHEN: Update whenever a phase status changes or the next action changes.
+-->
+[The single next action. Update whenever phase status changes.]
+
+## Current Phase
+<!-- 
+  WHAT: Which phase you're currently working on (e.g., "Phase 1", "Phase 3").
+  WHY: Quick reference for where you are in the task. Update this as you progress.
+-->
+Phase 1
+
+## Phases
+<!-- 
+  WHAT: Break your task into 3-7 logical phases. Each phase should be completable.
+  WHY: Breaking work into phases prevents overwhelm and makes progress visible.
+  WHEN: Update status after completing each phase: pending → in_progress → complete
+-->
+
+### Phase 1: Requirements & Discovery
+<!-- 
+  WHAT: Understand what needs to be done and gather initial information.
+  WHY: Starting without understanding leads to wasted effort. This phase prevents that.
+-->
+- [ ] Understand user intent
+- [ ] Identify constraints and requirements
+- [ ] Document findings in findings.md
+- **Status:** in_progress
+<!-- 
+  STATUS VALUES:
+  - pending: Not started yet
+  - in_progress: Currently working on this
+  - complete: Finished this phase
+-->
+
+### Phase 2: Planning & Structure
+<!-- 
+  WHAT: Decide how you'll approach the problem and what structure you'll use.
+  WHY: Good planning prevents rework. Document decisions so you remember why you chose them.
+-->
+- [ ] Define technical approach
+- [ ] Create project structure if needed
+- [ ] Document decisions with rationale
+- **Status:** pending
+
+### Phase 3: Implementation
+<!-- 
+  WHAT: Actually build/create/write the solution.
+  WHY: This is where the work happens. Break into smaller sub-tasks if needed.
+-->
+- [ ] Execute the plan step by step
+- [ ] Write code to files before executing
+- [ ] Test incrementally
+- **Status:** pending
+
+### Phase 4: Testing & Verification
+<!-- 
+  WHAT: Verify everything works and meets requirements.
+  WHY: Catching issues early saves time. Document test results in progress.md.
+-->
+- [ ] Verify all requirements met
+- [ ] Document test results in progress.md
+- [ ] Fix any issues found
+- **Status:** pending
+
+### Phase 5: Delivery
+<!-- 
+  WHAT: Final review and handoff to user.
+  WHY: Ensures nothing is forgotten and deliverables are complete.
+-->
+- [ ] Review all output files
+- [ ] Ensure deliverables are complete
+- [ ] Deliver to user
+- **Status:** pending
+
+## Key Questions
+<!-- 
+  WHAT: Important questions you need to answer during the task.
+  WHY: These guide your research and decision-making. Answer them as you go.
+  EXAMPLE: 
+    1. Should tasks persist between sessions? (Yes - need file storage)
+    2. What format for storing tasks? (JSON file)
+-->
+1. [Question to answer]
+2. [Question to answer]
+
+## Decisions Made
+<!-- 
+  WHAT: Technical and design decisions you've made, with the reasoning behind them.
+  WHY: You'll forget why you made choices. This table helps you remember and justify decisions.
+  WHEN: Update whenever you make a significant choice (technology, approach, structure).
+  EXAMPLE:
+    | Use JSON for storage | Simple, human-readable, built-in Python support |
+-->
+| Decision | Rationale |
+|----------|-----------|
+|          |           |
+
+## Errors Encountered
+<!-- 
+  WHAT: Every error you encounter, what attempt number it was, and how you resolved it.
+  WHY: Logging errors prevents repeating the same mistakes. This is critical for learning.
+  WHEN: Add immediately when an error occurs, even if you fix it quickly.
+  EXAMPLE:
+    | FileNotFoundError | 1 | Check if file exists, create empty list if not |
+    | JSONDecodeError | 2 | Handle empty file case explicitly |
+-->
+| Error | Attempt | Resolution |
+|-------|---------|------------|
+|       | 1       |            |
+
+## Notes
+<!-- 
+  REMINDERS:
+  - Update phase status as you progress: pending → in_progress → complete
+  - Re-read this plan before major decisions (attention manipulation)
+  - Log ALL errors - they help avoid repetition
+  - Never repeat a failed action - mutate your approach instead
+-->
+- Update phase status as you progress: pending → in_progress → complete
+- Re-read this plan before major decisions (attention manipulation)
+- Log ALL errors - they help avoid repetition