Save to Long-Term Memory

What it does

When your agent uses it

• Saving a decision or design rationale for later sessions
• Recording a fact together with the files it relates to
• Correcting a memory that was saved earlier with outdated information

Example prompts

• “Remember that we rotate JWT refresh tokens on every use and revoke the old one server-side.”
• “Save this for next time: the staging database resets every Sunday night.”
• “Note that the billing webhook handler lives in src/billing/webhook.ts.”

Requirements

• agentmemory with its `memory_save` tool available

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Pull the core insight, decision, or fact out of $ARGUMENTS.
2. 2Extract 2-5 lowercased concept phrases. Prefer specific over generic
3. 3Extract referenced file paths (absolute or repo-relative). Empty if none.
4. 4Call memory_save with content, concepts (comma-separated string), and
5. 5Confirm the save and echo the concepts so the user knows the retrieval terms.
6. 6To update a fact, save the corrected version outright: near-duplicate content

What it can do on your machine

Read from SKILL.md and the folder at commit 007a1a7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Save to Long-Term Memory loads about 600 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 235 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~600

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rohitg00/agentmemory at commit 007a1a7, republished under its Apache-2.0 licence (© rohitg00). 235 words, ~600 tokens.

name

remember

description

Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to preserve knowledge for future sessions.

argument-hint

[what to remember]

user-invocable

true

memory_save {
  "content": "We rotate JWT refresh tokens on every use; the old token is revoked server-side in auth/refresh.ts.",
  "concepts": "jwt-refresh-rotation, token-revocation, auth-flow",
  "files": "src/auth/refresh.ts"
}

Saved memory abc12345 with 3 concepts: jwt-refresh-rotation, token-revocation, auth-flow.

© rohitg00, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugin/skills/remember of rohitg00/agentmemory.

• SKILL.md
• EXAMPLES.md

Open the folder on GitHubat commit 007a1a7