Skip to content
Agentmart
Submit a tool

memory

Read, add, replace, or remove user/org memory entries via the `memory` tool.

Skill by iarmankhan

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/iarmankhan-memory

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Read, add, replace, or remove user/org memory entries via the `memory` tool. Use sparingly — only persist information that is non-obvious, durable across sessions, and relevant to future work. Never persist secrets or PII you did not need to handle.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/memory

What's inside

Skill name
memory
Description
Read, add, replace, or remove user/org memory entries via the `memory` tool. Use sparingly — only persist information that is non-obvious, durable across sessions, and relevant to future work. Never persist secrets or PII you did not need to handle.
License
MIT
Instructions
29 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# memory

The `memory` tool persists facts across sessions. Two scopes:

- `target=user` — preferences and context about the current human user. Scoped `(org_id, user_id)`.
- `target=org` — facts about the org's codebase, conventions, or systems. Scoped `(org_id)`. Org writes typically go through draft review.

Operations:

- `read` — fetch all entries for the scope.
- `add { content }` — add a new entry.
- `replace { id, content }` — replace one.
- `remove { id }` — delete one.

When to write:

- The user told you a preference you should respect in future sessions ("I want terse output", "always use pnpm").
- You learned a load-bearing fact about the codebase the agent didn't know ("auth tokens live in services/auth/tokens.ts, not in middleware").

When NOT to write:

- Anything ephemeral about the current task.
- Anything you can read from the codebase or git history right now.
- Anything you've been told only once in passing.
- Secrets, credentials, or PII.

Memory writes are scanned for prompt-injection patterns and char-bounded. If the harness rejects your write, refine — don't retry verbatim.

From iarmankhan/zuno, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 25, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from iarmankhan

Cite this page

memory skill. Agent Mart. https://agentmart.dev/skills/iarmankhan-memory (last updated 2026-10-24)