memory

memory is a command for Claude Code from rtazima/claude-proj-blueprint. It costs 0 tokens per session (283 once invoked), scanned A, original, MIT.

A command for managing long-term project memory, including indexing saved knowledge, searching it, and viewing memory statistics.

In plain words
What is it for?
Use it to index project changes, search project or shared memory, retrieve results in an agent-friendly format, and inspect how much information is stored.
Why use it?
It lets an agent reuse decisions and past project information instead of rediscovering them, while identifying the source of retrieved context.

Command for Claude Code

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/rtazima/claude-proj-blueprint/memory
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

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/rtazima/claude-proj-blueprint/memory.svg)](https://agentmods.dev/commands/rtazima/claude-proj-blueprint/memory)
Your own site
<a href="https://agentmods.dev/commands/rtazima/claude-proj-blueprint/memory"><img src="https://agentmods.dev/badge/commands/rtazima/claude-proj-blueprint/memory.svg" alt="Measured on agentmods" height="20"></a>
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 283 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 $0.00283
Opus 5 $0.00000 $0.00142
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00028

Measured 5d ago against content hash 476d2fecf905, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 5d 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 · 24 lines

What it actually says

Long-term memory operations for the project.

Arguments: $ARGUMENTS (subcommand: index | search | stats)

Flags: --global Search/show global cross-project memory instead of project memory --both Search both project and global memory, merge results by relevance

Workflow:

  1. If "index": run python memory/index.py --incremental to re-index changes (ADRs, post-mortems, and learner reports auto-promote to global memory if enabled)
  2. If "search ": run python memory/query.py "<query>" --agent-format and use as context
  3. If "search --global ": run python memory/query.py "<query>" --global --agent-format
  4. If "search --both ": run python memory/query.py "<query>" --both --agent-format
  5. If "stats": run python memory/query.py --stats to see chunk counts
  6. If "stats --global": run python memory/query.py --stats --global to see global memory

After searching, use the results as context for responding to the user. Always cite the source (file and excerpt) when using information from memory.

If the memory module is not installed, instruct: pip install -r memory/requirements.txt python memory/index.py

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. 5d ago First seen · 24 lines · 0 tokens per session scan A 476d2fecf905

Subscribe to this mod's changes

memory is a command published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 283 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.