Agent Memory Discipline

Agent Memory Discipline is an AI Engineering skill for Claude Code, published by davepoon in buildwithclaude.

3.3K stars459 forkson davepoon/buildwithclaudeAdded 2026/08/17Repository updated 2026/08/16

claudeclaude-codeclaude-code-commandsclaude-skillscli-toolcommandsmcpmcp-servermcp-toolsopenclawplugin-marketplacesubagents

Install in seconds

Install Agent Memory Discipline

Copy Agent Memory Discipline into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/davepoon/buildwithclaude/tree/main/plugins/all-skills/skills/agent-memory-discipline ~/.claude/skills/agent-memory-discipline

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/davepoon/buildwithclaude.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/all-skills/skills/agent-memory-discipline/SKILL.md in davepoon/buildwithclaude
Installs to: ~/.claude/skills/agent-memory-discipline
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Memory Discipline does

Agent Memory Discipline teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use it when a memory tool is connected but underused or when setting up persistent memory for a project.

Agent Memory Discipline is cataloged under AI Engineering on DirSkills. Agent Memory Discipline comes from a repository tagged claude, claude-code, claude-code-commands, claude-skills and cli-tool.

Documentation

README

Excerpt

Agent memory discipline

Connecting a memory tool does not make an agent use it. Tools register, the session runs, and nothing gets recalled or saved. This skill supplies the missing part: standing rules for when to read memory and when to write it.

It is backend-agnostic. Everything below works the same whether memory is a folder of Markdown files, a local MCP server, or a hosted service.

Recall before acting

Read memory before doing any of these, not after:

starting work on a project you have touched before
choosing a library, pattern, or tool
writing tests, commits, or documentation, where conventions apply
answering "how do we usually do X here"
anything the user phrases as "again", "like last time", or "as we agreed"

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agent Memory Discipline

What else does davepoon publish alongside Agent Memory Discipline?
Agent Memory Discipline is one of 25 skills that DirSkills catalogs from davepoon/buildwithclaude, the repository it ships in. Its siblings there include ActiveCampaign Automation, Agent Analytics and Airtable Automation. Each one is a separate skill with its own page in this directory, installs the same way Agent Memory Discipline does, and is maintained by davepoon in that same repository. The rest of the collection is listed on the davepoon/buildwithclaude page.
How does Agent Memory Discipline compare to other AI Engineering skills?
Agent Memory Discipline ranks #622 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Memory Discipline against them. Open each page to compare what they document and how they install.