memory

A command for saving and recalling information through three memory levels: temporary scratch notes, searchable project documentation, and long-term decisions. HITL means a person must approve writes to the long-term decision layer.

In plain words
What is it for?
Saving notes to scratch, recalling files or project facts, recording or retrieving decisions and history, and routing each request to the relevant memory layer.
Why use it?
It keeps short-lived notes, searchable project facts, and important decisions separate, so later lookups can use the appropriate source.

Command for Codex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/othmanadi/mddesign/memory
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/MDDesign

Made for: Codex.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.00424
Opus 5 $0.00024 $0.00212
Sonnet 5 $0.00010 $0.00085
Haiku 4.5 $0.00005 $0.00042

Measured 2d ago against content hash 726291fa728c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.codex/commands/memory.md · 39 lines

What it actually says

/mddesign:memory

Three-tier memory operations.

Save

/mddesign:memory save <text> (default tier: scratch)

Appends to .agents/memory/scratch/<topic>.md where <topic> is the active phase id from task_plan.md, or general if no plan. Fast, low-stakes, session-scoped.

/mddesign:memory save --tier why <text>

Proposes a promotion to MemPalace WHY tier. HITL gate before write. On approval, invokes /memory-router with MemPalace save pattern.

/mddesign:memory save --tier where <text>

WHERE is populated by QMD automatically when it indexes project markdown. Explicit write is rarely needed; this sub-command exists for completeness and is rate-limited to one-line annotations.

Recall

/mddesign:memory recall <query>

Routes based on query prefix:

  • "where", "which file", "find", "locate" → WHERE via /memory-router
  • "why", "decision", "history", "what did we decide" → WHY via /memory-router
  • Otherwise → peek at scratch first, fall back to WHERE

Always prints the source tier next to each result.

Boundaries

  • Never edits task_plan.md, findings.md, or progress.md.
  • Scratch lives in .agents/memory/scratch/. Never elsewhere.
  • MemPalace writes always HITL gated.

See skills/memory-layer/SKILL.md for full routing logic and conventions.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 39 lines · 48 tokens per session scan A 726291fa728c

Subscribe to this mod's changes

memory is a command published in the GitHub repository OthmanAdi/MDDesign (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 424 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.