memory

memory is a command for Claude Code from Smirnov-Labs/claude-skills. It costs 9 tokens per session (929 once invoked), scanned A, original, MIT.

A command for maintaining a project memory bank: a set of files that records the project’s goals, technical choices, working patterns, current context, and progress.

In plain words
What is it for?
Use it to review memory files, update project knowledge, archive completed work, and shorten notes that have grown too long.
Why use it?
It helps keep project notes current and moves completed or outdated information out of active files, reducing confusion when work continues later.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review memory files, update project knowledge, archive completed work, and shorten notes that have grown too long.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/smirnov-labs/claude-skills/memory
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.

Clone the repo
git clone --depth 1 https://github.com/Smirnov-Labs/claude-skills

Made for: Claude Code.

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 memory

README.md
[![agentmods](https://agentmods.dev/badge/commands/smirnov-labs/claude-skills/memory/github.svg)](https://agentmods.dev/commands/smirnov-labs/claude-skills/memory)
Your own site
<a href="https://agentmods.dev/commands/smirnov-labs/claude-skills/memory"><img src="https://agentmods.dev/badge/commands/smirnov-labs/claude-skills/memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for memory

Your own site · 80×15
<a href="https://agentmods.dev/commands/smirnov-labs/claude-skills/memory"><img src="https://agentmods.dev/badge/commands/smirnov-labs/claude-skills/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 929 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00009 $0.00929
Opus 5 $0.00005 $0.00464
Sonnet 5 $0.00002 $0.00186
Haiku 4.5 $0.00001 $0.00093

Measured 9d ago against content hash 8865d6809e0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

.claude/commands/memory.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Bank Update Command

Follow this comprehensive process to update and maintain the memory bank:

Step 1: Review All Memory Bank Files

Read and analyze ALL memory bank files in order:

  1. .claude/memory-bank/memory-rules.md
  2. .claude/memory-bank/projectbrief.md
  3. .claude/memory-bank/productContext.md
  4. .claude/memory-bank/systemPatterns.md
  5. .claude/memory-bank/techContext.md
  6. .claude/memory-bank/activeContext.md
  7. .claude/memory-bank/progress.md

As you review, identify:

  • Outdated information that needs updating
  • Completed items that should be archived
  • New patterns or insights to document
  • Information that's grown too long and needs compression

Step 2: Check for Compression Opportunities

Look for data that should be compressed or archived:

  • activeContext.md: Move completed work to progress.md, keep only active items
  • progress.md: Summarize long lists of completed items, group by milestones
  • systemPatterns.md: Consolidate similar patterns, remove obsolete approaches
  • techContext.md: Archive deprecated dependencies, consolidate setup instructions

Step 3: Update Files Systematically

Update each file that needs changes:

Priority Updates (do these first):

  1. activeContext.md - Update current focus, move completed work to progress.md
  2. progress.md - Add completed items, compress old accomplishments, update status

Secondary Updates (if needed):

  1. systemPatterns.md - Document new patterns discovered, remove outdated approaches
  2. techContext.md - Update dependencies, setup steps, infrastructure changes
  3. productContext.md - Update if product direction or requirements changed
  4. projectbrief.md - Only update if core project scope changed

Step 4: Compress Old Data

When files become too long or cluttered:

For activeContext.md:

  • Keep only current and next 1-2 sprints of work
  • Move completed items to progress.md
  • Summarize old decisions, keep only key points

For progress.md:

  • Group old completed items by major milestones
  • Summarize lists that exceed 15-20 items
  • Keep recent work detailed, compress older work

Read the full file on GitHub · 121 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. 9d ago First seen · 121 lines · 9 tokens per session scan A 8865d6809e0c

Subscribe to this mod's changes

memory is a command published in the GitHub repository Smirnov-Labs/claude-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 9 tokens to every session and 929 once invoked, about $0.0000 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.