save

A command for saving information to topic-specific memory files for use in later sessions. It checks existing notes, avoids duplicates, and updates the memory index when needed.

In plain words
What is it for?
Use it when you want the agent to remember a decision, instruction, project detail, or other useful context.
Why use it?
It prevents important context from being lost between conversations and keeps saved notes organized.

Command

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/helloruru/claude-memory-engine/save
Clone the repo
git clone --depth 1 https://github.com/HelloRuru/claude-memory-engine
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 308 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 $0.00000 $0.00308
Opus 5 $0.00000 $0.00154
Sonnet 5 $0.00000 $0.00062
Haiku 4.5 $0.00000 $0.00031

Measured 2d ago against content hash 055ec1295750, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

save 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.

commands/save.md · 26 lines

What it actually says

/save -- Save Memory Across Sessions

Store information so the next session's Claude knows about it. The core mission: make sure the next conversation doesn't lose this knowledge.

Steps

  1. Dedup check -- Search existing memory files (memory/*.md) for related content. If found, update that section instead of creating a new entry
  2. Route to the right file -- Determine which memory file this belongs to based on topic. If unclear, ask the user
  3. Skip if already in CLAUDE.md -- CLAUDE.md is auto-loaded every session, so don't duplicate its content
  4. Never write directly to MEMORY.md -- MEMORY.md is an index of pointers, not a content store. Save content to topic-specific files in memory/
  5. Report -- Tell the user: "Saved to {filename}, section {section name}" or "Updated {filename}, changed {what}"

Memory File Organization

Memory uses a hub-and-spoke model:

  • MEMORY.md = the hub (index with pointers to topic files, max 200 lines)
  • memory/*.md = the spokes (topic-specific content files)

When MEMORY.md exceeds 170 lines, proactively suggest moving content to separate files.

Notes

  • User says "save" or "remember this" -> just save it, don't question it
  • Always check for duplicates before creating new entries
  • Use natural language, not technical jargon
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 · 26 lines · 0 tokens per session scan A 055ec1295750

Subscribe to this mod's changes

save is a command published in the GitHub repository HelloRuru/claude-memory-engine (133 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 308 tokens. 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.