agent-memory-file

Create and maintain AI-agent memory files like CLAUDE.md and AGENTS.md.

1|Updated Jun 3, 2026
One-click install
npx skills add https://github.com/tanveerriaz/Skillz --skill agent-memory-file-tanveerriaz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-memory-file
Source: https://github.com/tanveerriaz/Skillz/tree/main/skills/agent-memory-file
Command: npx skills add https://github.com/tanveerriaz/Skillz --skill agent-memory-file-tanveerriaz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI coding agents lose project context between sessions, re-deriving the stack, conventions, and rules inconsistently each time. This Skill defines what belongs in a durable agent memory file so every session starts from the same ground truth. ## Core Features & Use Cases - Structured memory file authoring: Covers project overview, pinned stack, folder structure, conventions, workflow rules, and guardrails in one canonical file. - Multi-tool support: Applies to CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, and copilot-instructions.md, with guidance on keeping one canonical source. - Quality and safety guardrails: Includes a checklist and rules preventing secrets, confidential data, and bloated low-signal content. - Use Case: You start a new SaaS repo that multiple AI tools will work on. Use this Skill to write a 60-line AGENTS.md that pins the stack, maps the structure, states the branch policy, and lists guardrails every agent must honor. ## Quick Start Create an AGENTS.md memory file for my project that captures the stack, folder structure, conventions, and guardrails an AI agent needs every session.

Frequently Asked Questions about agent-memory-file

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a CLAUDE.md or AGENTS.md file for my project?▼

Start with a one-paragraph project overview, then pin the tech stack, map the folder structure, state coding conventions and test commands, define workflow rules like branch policy, and list guardrails as short imperatives. Keep the file concise since agents read it every session.

What should go in an AI agent memory file?▼

Include the project overview, pinned stack with non-negotiables, structure and where things belong, conventions and test commands, workflow rules, and guardrails. Exclude secrets, credentials, full API references, changelogs, and other low-signal content.

Can I use one memory file for Claude Code, Cursor, and Copilot?▼

Yes. Keep one canonical memory file such as AGENTS.md and have other tool-specific files like CLAUDE.md or copilot-instructions.md reference it. This prevents drift when multiple AI tools work on the same project.

How do I handle agent memory files in a monorepo?▼

Use a root-level memory file covering shared stack, conventions, and guardrails, then add scoped per-package notes for package-specific rules. This keeps the root file lean while giving agents the local context they need.

Why is my AI agent ignoring project conventions between sessions?▼

Agents have no persistent memory, so conventions must live in a memory file loaded at session start. If rules are scattered, unstated, or buried in a bloated file, agents miss them; consolidate them into one concise canonical file.