Converts a PRD or requirements document into a structured, phased implementation plan with individual phase files and granular per-task files written to .context/plans/. Also restructures existing monolithic planning documents into digestible, hierarchical directory structures. Creates a root plan index summarising all phases, a numbered phase file per phase, and a numbered task file per task inside each phase directory.
92
93%
Does it follow best practices?
Impact
91%
3.25xAverage score across 5 eval scenarios
Passed
No known issues
#!/usr/bin/env sh
# Usage: new-plan.sh <slug>
# Creates: .context/plans/plan-<slug>/README.md
set -eu
SLUG="${1:?Usage: new-plan.sh <slug>}"
BASE=".context/plans/plan-${SLUG}"
mkdir -p "${BASE}/phases"
cat > "${BASE}/README.md" <<EOF
# Implementation Plan — ${SLUG}
## Goal
<!-- One paragraph: what the project builds, value delivered, and target users. -->
## Phases
| # | Phase | Status | Tasks |
|---|---|---|---|
## Constraints
<!-- Bullet list of non-negotiable technical, timeline, or resource constraints. -->
## References
<!-- Links to PRD, architecture docs, or ADRs. -->
EOF
echo "Created ${BASE}/README.md"