meta-mode-memory

Store and query compact task-state memory files in Codex repositories.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/amaledtuning/CODEX_Skills --skill meta-mode-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meta-mode-memory
Source: https://github.com/amaledtuning/CODEX_Skills/tree/main/skills/meta-mode-memory
Command: npx skills add https://github.com/amaledtuning/CODEX_Skills --skill meta-mode-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

File-first memory sandbox for Codex. Stores compact durable task-state snapshots, ingests docs, and compiles deterministic knowledge pages, with query and lint/audit support.

Core Features & Use Cases

  • File-first memory sandbox for compact, durable task-state memory in the repo without external services, hooks, or model-dependent indexing.
  • Ingest markdown or text docs into memory inbox/ingest.
  • Compile deterministic knowledge pages and run audits for structure and markdown-link health.

Quick Start

Use save_note.py to capture a concise memory note into today's daily log and optionally create a checkpoint with session_checkpoint.py.

Frequently Asked Questions about meta-mode-memory

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

FAQPage Schema
How do I store durable task-state memory for Codex workflows without external services?

You can store durable task-state memory by using a file-first memory sandbox that writes compact snapshots directly into a local repository under a `.codex-memory` directory without requiring external services or model-dependent indexing.

What is the best way to ingest markdown documentation into a local repository memory system?

The best way to ingest markdown documentation is to use a memory ingestion tool that imports docs into a local memory inbox, enabling subsequent querying and compilation of deterministic knowledge pages.

How do I create a checkpoint to save implementation notes during a coding session?

You create a checkpoint by running a dedicated script like `session_checkpoint.py` to capture concise memory notes into a daily log, preserving implementation state within your repository.

Can I run an audit on markdown link health and structure for my local knowledge pages?

Yes, you can run an audit to check markdown link health and structural integrity, ensuring that compiled deterministic knowledge pages remain valid and accessible within your local memory layout.

Do I need external dependencies or hooks to maintain a file-first memory sandbox?

No, you do not need external dependencies or hooks to maintain a file-first memory sandbox, as it enforces a local file layout with optional overrides and operates entirely self-contained.

How does deterministic knowledge compilation work for local task-state snapshots?

Deterministic knowledge compilation works by processing ingested markdown and text documents into structured knowledge pages, ensuring consistent output structure and markdown-link health for auditing.