policy

policy is a skill for Claude Code, Codex from mem0ai/mem0. It costs 60 tokens per session (652 once invoked), scanned A, original, Apache-2.0.

A project settings tool for Mem0's memory rules. It shows or changes the instructions that say what the agent should remember or ignore, stored in a version-controlled mem0.md file.

In plain words
What is it for?
Use it to view, set, replace, or clear memory rules, including separate instructions for agent-specific memories.
Why use it?
It gives the team one shared place to control memory extraction. This reduces unwanted memories and makes the rules consistent across sessions.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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 skills/mem0ai/mem0/policy
Any agent
npx skills add mem0ai/mem0 --skill policy
Clone the repo
git clone --depth 1 https://github.com/mem0ai/mem0

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/mem0ai/mem0/policy.svg)](https://agentmods.dev/skills/mem0ai/mem0/policy)
Your own site
<a href="https://agentmods.dev/skills/mem0ai/mem0/policy"><img src="https://agentmods.dev/badge/skills/mem0ai/mem0/policy.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 652 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 $0.00060 $0.00652
Opus 5 $0.00030 $0.00326
Sonnet 5 $0.00012 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured 4d ago against content hash 57659d82eed5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

policy 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 4d 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.

integrations/mem0-plugin/skills/policy/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mem0 Policy

The project's memory policy lives in a ## Instructions section of mem0.md at the repo root. It is version-controlled and shared by the whole team, and it maps to Mem0's custom_instructions (what to extract / ignore). An optional ## Agent Instructions section maps to agent_custom_instructions (guidance for agent-scoped memories only).

The policy takes effect on the next session (mem0.md is re-parsed on SessionStart) and is applied automatically on the plugin's memory writes.

Execution

Step 1: Determine intent from the argument

/mem0:policy is invoked as /mem0:policy [<subcommand>] <text>:

Argument Action
(none) or show Show the current policy
set <text> or free text Set/replace the ## Instructions (custom) policy
agent <text> Set/replace the ## Agent Instructions policy
clear Remove both policy sections

Step 2: Locate mem0.md

mem0.md sits at the repo root (the current working directory). If it does not exist yet and the user is setting a policy, you will create it.

Step 3a: Show

Run python3 "$CLAUDE_PLUGIN_ROOT/scripts/parse_mem0_config.py" --key instructions . and --key agent_instructions . (or read mem0.md directly). Print:

Memory policy for this project (mem0.md):
  Instructions:       <text, or "(none)">
  Agent Instructions: <text, or "(none)">

If mem0.md is absent, say there is no policy yet and offer to set one.

Step 3b: Set / clear

Edit mem0.md, adding or replacing the target section. Keep the instruction a short prose paragraph (what to remember, what to ignore). Example:

## Instructions
Remember architecture decisions, API contracts, and team conventions.
Ignore transient debugging output, stack traces, and anything resembling a secret.
  • Preserve any other existing sections (## Retention, ## Categories, etc.).
  • If the section already exists, replace its body; otherwise append the section.
  • For clear, delete the ## Instructions and ## Agent Instructions sections.

Read the full file on GitHub · 72 lines

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. 4d ago First seen · 72 lines · 60 tokens per session scan A 57659d82eed5

Subscribe to this mod's changes

policy is a skill published in the GitHub repository mem0ai/mem0 (64,662 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 652 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

browserwing-executor

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

MemTensor/MemOS · 42 tokens

dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…

MemTensor/MemOS · 84 tokens

ask-user-question

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

MemTensor/MemOS · 44 tokens

memos-memory-guide

Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query…

MemTensor/MemOS · 131 tokens

browserwing-admin

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

MemTensor/MemOS · 47 tokens

safe-file-deletion

Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from disk. MUST be followed for all delete operations.

MemTensor/MemOS · 46 tokens