memory

memory is a command for Claude Code from boparaiamrit/skills-by-amrit. It costs 16 tokens per session (1,229 once invoked), scanned A, original, MIT.

A project memory management command that stores decisions, architecture notes, known problems, and handoffs in a .planning directory.

In plain words
What is it for?
Use it to initialize, read, update, compress, or check the status of the project's saved notes and session history.
Why use it?
It preserves useful context between coding sessions so work can continue without rebuilding the same understanding each time.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit Use it to initialize, read, update, compress, or check the status of the project's saved notes and session history.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/boparaiamrit/skills-by-amrit/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/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 agents.

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/boparaiamrit/skills-by-amrit/memory/github.svg)](https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/memory)
Your own site
<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/memory"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/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/boparaiamrit/skills-by-amrit/memory"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,229 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 $0.00016 $0.01229
Opus 5 $0.00008 $0.00615
Sonnet 5 $0.00003 $0.00246
Haiku 4.5 $0.00002 $0.00123

Measured 9d ago against content hash 343d3ebebbcf, 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.

commands/memory.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/memory — Persistent Memory Management

Manage the project's persistent memory system. This command handles reading, writing, and maintaining the .planning/ memory directory.

Usage

  • /memory init — Initialize memory for a new project
  • /memory read — Read current memory and display context
  • /memory write — Write session learnings to memory
  • /memory compress — Compress memory when it grows too large
  • /memory status — Show memory system status

Protocol

Initialization (init)

  1. Create .planning/ directory structure:

    • MEMORY.md — project brain
    • sessions/ — session logs
    • sessions/_archive/ — archived sessions
    • decisions/DECISIONS.md — decision log
    • context/architecture.md — architecture notes
    • context/patterns.md — code patterns
    • context/gotchas.md — known issues
    • context/tech-debt.md — technical debt
    • handoffs/LATEST.md — last session handoff
    • handoffs/_history/ — archived handoffs
  2. Codebase Scan Algorithm:

    a. DETECT PROJECT TYPE:
       - package.json → Node.js/JavaScript/TypeScript
       - requirements.txt/pyproject.toml → Python
       - go.mod → Go
       - Cargo.toml → Rust
       - pom.xml/build.gradle → Java
       - *.sln/*.csproj → .NET
    
    b. EXTRACT TECH STACK:
       - Parse dependency files for frameworks
       - Identify major libraries
       - Note database connections (if visible)
    
    c. ANALYZE STRUCTURE:
       - Count files by extension
       - Identify source and test directories
       - Note documentation presence
    
    d. GENERATE MEMORY:
       - Write project overview
       - Document detected architecture
       - List identified patterns
    
  3. Write initial content to all context files

Read (read)

  1. Read .planning/MEMORY.md
  2. Read .planning/handoffs/LATEST.md (if exists — skip if missing)
  3. Display a summary of project context
  4. Note any open items or blockers from last session

Write (write)

  1. Archive previous handoff:
    • If handoffs/LATEST.md exists, move to handoffs/_history/YYYY-MM-DD-HHMMSS.md

Read the full file on GitHub · 164 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 · 164 lines · 16 tokens per session scan A 343d3ebebbcf

Subscribe to this mod's changes

memory is a command published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,229 once invoked, about $0.0001 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.