AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Plan Memory Hierarchy

skill-jh941213-codex-lattice-plan-memory-hierarchy · by jh941213

Create backend/frontend layered `.md` memory during Plan mode. Use when request includes requirements capture, memory bootstrap, or plan preparation with backend/frontend separation.

↗ Repository
— No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-jh941213-codex-lattice-plan-memory-hierarchy

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-jh941213-codex-lattice-plan-memory-hierarchy)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
○ 4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Plan Memory Hierarchy? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Layered Project Memory

This skill creates and maintains structured markdown memory files at project start, then reuses them during planning and execution.

Runtime Rules

  1. Confirm the project root. If unclear, ask the user.
  2. If .plan-memory/ does not exist, run bootstrap script.
python3 scripts/bootstrap_plan_memory.py --root . --project-name ""
  1. Read core memory files:
  • .plan-memory/README.md
  • .plan-memory/product/requirements.md
  • .plan-memory/backend/requirements.md
  • .plan-memory/frontend/requirements.md
  • .plan-memory/shared/constraints.md
  1. Store new information in the most relevant layer file, not in a single aggregate file.
  2. Before final plan output, update .plan-memory/README.md summary index.

Use Cases

  • New project intake with requirements capture
  • Splitting work by backend/frontend scope
  • Long-running refactor/integration work requiring persistent context

스크립트 동작

Default directory tree

.plan-memory/
  README.md
  product/requirements.md
  product/acceptance-criteria.md
  backend/requirements.md
  backend/api-contracts.md
  backend/data-model.md
  frontend/requirements.md
  frontend/ux-flow.md
  frontend/state-management.md
  shared/constraints.md
  shared/glossary.md
  execution/current-plan.md
  execution/open-questions.md

Key Rules

  • Existing files are preserved by default; do not overwrite unless --force is passed.
  • For edits, ask for user confirmation before deleting/replacing existing docs.
  • For new projects, fill execution/current-plan.md and product/acceptance-criteria.md first.

Maintenance Rules

  • Keep backend and frontend assumptions separate.
  • Put cross-cutting rules (security/performance/compliance) in shared/constraints.md.
  • Keep the summary index in README.md in sync with added layers/files.
  • End each planning pass by writing plan/risk/acceptance updates into execution/current-plan.md.

스크립트 위치

  • /Users/kdb/.codex/skills/plan-memory-hierarchy/scripts/bootstrap_plan_memory.py

Failure Handling

  • Stop and ask for confirmation if root is unclear.
  • On filesystem errors, report exact failed path and error message.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills