memory

A command for managing memory files: persistent notes that give AI coding tools context across sessions.

In plain words
What is it for?
Use it to list, create, import, or export memory files stored in .ai/memory/.
Why use it?
It keeps shared project knowledge in one central location and can move it between different tools' file formats.

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/thethoughtagen/agentsync/memory
Clone the repo
git clone --depth 1 https://github.com/TheThoughtagen/agentsync
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 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 $0.00016 $0.00303
Opus 5 $0.00008 $0.00151
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured yesterday against content hash 16ccda545a72, 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 yesterday.

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.

plugins/aisync/commands/memory.md · 41 lines

What it actually says

/aisync:memory

Manage memory files in .ai/memory/. Accepts a subcommand argument: list, add, import, or export.

Usage

List memory files

aisync memory list

Run this to display all memory files in .ai/memory/. Present each file's name and a brief description of its contents.

Add a memory file

aisync memory add <name> [--content <content>]

Run with the user's specified name to create a new memory file in .ai/memory/.

Import memory

aisync memory import

Run this to import memory/context files from tool-native locations into .ai/memory/. Report which files were imported and from which tools.

Export memory

aisync memory export

Run this to export .ai/memory/ files to tool-native locations. Report which files were written and to which tools.

Notes

  • Memory files are markdown files in .ai/memory/ that provide persistent context across sessions.
  • These are synced to tool-native locations (e.g., .claude/memory/, .cursor/context/) via /aisync:sync.
  • Always edit memory files in .ai/memory/, not in tool-native copies.
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. yesterday First seen · 41 lines · 16 tokens per session scan A 16ccda545a72

Subscribe to this mod's changes

memory is a command published in the GitHub repository TheThoughtagen/agentsync (2 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 303 once invoked, about $0.0001 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 2026-08-31.