memory-update

A command for keeping concise project knowledge in permanent memory files covering architecture, conventions, dependencies, and decisions.

In plain words
What is it for?
Use it after significant changes, important discoveries, complex fixes, or whenever project memory needs a focused update.
Why use it?
It preserves important discoveries and the current project state between work sessions without maintaining lengthy history.

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/stefan-jansen/claude-code-toolkit/memory-update
Clone the repo
git clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 696 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 $0.00000 $0.00696
Opus 5 $0.00000 $0.00348
Sonnet 5 $0.00000 $0.00139
Haiku 4.5 $0.00000 $0.00070

Measured 2d ago against content hash fe43a6820fe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-update 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 2d 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.

plugins/memory/commands/memory-update.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Update

Incrementally maintain project knowledge in permanent memory files.

Purpose

Regular housekeeping to capture learnings and maintain accurate project state without cluttering documentation with verbose histories.

What Gets Updated

Core Memory Files

Located in .claude/memory/:

  1. project_state.md - Current architecture, scope, key components
  2. conventions.md - Code patterns, naming standards, practices
  3. dependencies.md - External services, APIs, integrations
  4. decisions.md - Architectural choices and rationale

Update Triggers

  • After implementing significant features
  • When discovering important patterns
  • Before conversation context fills (proactive)
  • After resolving complex issues

Usage

# Analyze and update all relevant memory files
/memory-update

# Update specific aspect
/memory-update "new authentication architecture"

# Quick update (only critical changes)
/memory-update --quick

Memory Principles

Keep It Concise

❌ "We initially tried approach X, then switched to Y because..." ✅ "Uses pattern Y for better performance"

Focus on Current State

❌ "Previously the system used MySQL but we migrated..." ✅ "PostgreSQL database with TimescaleDB extension"

Avoid Meta-Commentary

❌ "This was updated on Sept 15 after discussion about..." ✅ Just the fact/decision itself

Use References, Not Duplication

❌ Copying full documentation into memory ✅ "See @.claude/reference/api-spec.md for details"

Update Process

I'll:

  1. Analyze recent work for durable learnings
  2. Update relevant memory files with new knowledge
  3. Ensure CLAUDE.md references are current
  4. Remove outdated information if any

Example Memory Structure

project_state.md

# Project State

## Architecture
- Microservices: auth, payments, analytics
- Event-driven with RabbitMQ
- PostgreSQL + Redis caching

## Current Scope
- Real-time data processing
- Business logic implementation
- Performance monitoring

Read the full file on GitHub · 133 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. 2d ago First seen · 133 lines · 0 tokens per session scan A fe43a6820fe0

Subscribe to this mod's changes

memory-update is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 696 tokens. 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.