approve
Approve the current PRD and begin parallel story execution. Analyzes dependencies, creates execution batches, launches background Task agents for each story,…
Diagnose decision conflicts, duplicates, and superseded entries across all design documents. Helps maintain decision hygiene as the project evolves. Usage: /plan-cascade:memory-doctor
> /plugin marketplace add Taoidle/plan-cascade > /plugin install plan-cascade@plan-cascade
How it fires
How this command gets triggered: by you, by Claude, or both.
/memory-doctorContext preview
What this command does when you run it.
Diagnose decision conflicts, duplicates, and superseded entries across all design documents. Helps maintain decision hygiene as the project evolves. Usage: /plan-cascade:memory-doctor
description: "Diagnose decision conflicts, duplicates, and superseded entries across all design documents. Helps maintain decision hygiene as the project evolves. Usage: /plan-cascade:memory-doctor"
You are running a full diagnosis on all Architecture Decision Records (ADRs) across the project's design documents.
**CRITICAL**: Use Bash to run the memory doctor script in full diagnosis mode:
uv run python "${CLAUDE_PLUGIN_ROOT}/skills/hybrid-ralph/scripts/memory-doctor.py" \
--mode full \
--project-root "$(pwd)"This script collects all decisions from every `design_doc.json` in the project (root, worktrees, feature directories) and uses LLM to detect conflicts, superseded entries, and semantic duplicates.
Exit code handling:
Display the full diagnosis report from Step 1 output. The report groups findings by type:
**CRITICAL**: For each diagnosis finding, use `AskUserQuestion` to let the user choose an action:
**For CONFLICT findings:**
**For SUPERSEDED findings:**
**For DUPLICATE findings:**
Present each finding with its explanation and suggestion from the diagnosis report. Example question:
> **ADR-F003 vs ADR-F012**: Two decisions conflict on API response format. > Old: "API uses custom JSON structure" (feature-auth/design_doc.json) > New: "API uses JSON:API spec" (feature-order/design_doc.json) > Suggestion: Deprecate ADR-F003 > > How would you like to resolve this?
**CRITICAL**: Construct a JSON array of the user's choices and invoke the script to apply them.
Save the user's choices to a temporary file `_doctor_actions.json`:
[
{
"action": "deprecate",
"diagnosis": {
"type": "conflict",
"decision_a": {"id": "ADR-F003", "_source": "path/to/design_doc.json"},
"decision_b": {"id": "ADR-F012"},
"source_a": "path/to/design_doc.json",
"source_b": "other/design_doc.json"
}
}
]Then run:
uv run python "${CLAUDE_PLUGIN_ROOT}/skills/hybrid-ralph/scripts/memory-doctor.py" \
--apply _doctor_actions.json \
--project-root "$(pwd)"Clean up the temporary file after execution:
rm -f _doctor_actions.json
Display a summary of all actions taken:
Memory Doctor — 处理结果 ━━━━━━━━━━━━━━━━━━━━━━━━ ✓ Deprecated: N decisions ✓ Merged: N decision pairs ○ Skipped: N findings
If any design_doc.json files were modified, list them so the user knows which files changed.
After the diagnosis is complete:
AI-Powered Cascading Development Framework Transform complex projects into parallel executable tasks with intelligent decomposition and multi-provider execution Why Plan Cascade? • Product Editions • Quick Start • Architecture
Repo: Taoidle/plan-cascade
Approve the current PRD and begin parallel story execution. Analyzes dependencies, creates execution batches, launches background Task agents for each story,…
AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation,…
Check and update .gitignore to exclude Plan Cascade temporary files. Ensures planning files won't be accidentally committed to version control.
Complete a worktree task. Verifies all phases are complete, commits code changes (excluding planning files), merges to target branch, and removes worktree. Can…
Show execution status dashboard. Usage: /plan-cascade:dashboard [--verbose|-v] [--json]
Generate a technical design document. Auto-detects level: project-level from mega-plan.json, or feature-level from prd.json. Provides architectural context for…