memory

memory is a skill for Claude Code, Codex from rtazima/claude-proj-blueprint. It costs 52 tokens per session (425 once invoked), scanned A, original, MIT.

A long-term memory system that stores project information in a searchable vector database. It can search past decisions, solutions, code, documentation, and commits.

In plain words
What is it for?
Use it before implementing or reviewing changes, when investigating past incidents, or when searching for previous solutions and architectural decisions. It can also index new documentation and source changes.
Why use it?
It helps an agent recover relevant project history instead of repeating investigations or overlooking earlier design choices.

Skill for Claude CodeCodex

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 skills/rtazima/claude-proj-blueprint/memory
Any agent
npx skills add rtazima/claude-proj-blueprint --skill memory
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

Made for: Claude Code, Codex.

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/skills/rtazima/claude-proj-blueprint/memory.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/memory)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/memory"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 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 5.1 $0.00052 $0.00425
Opus 5 $0.00026 $0.00212
Sonnet 5 $0.00010 $0.00085
Haiku 4.5 $0.00005 $0.00042

Measured 5d ago against content hash 1e84b26122a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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/skills/memory/SKILL.md · 57 lines

What it actually says

Long-Term Memory

When to use

  • Before implementing: search for previous solutions to similar problems
  • Before deciding: search for already-documented ADRs and trade-offs
  • After incidents: search for post-mortems of similar issues
  • When reviewing: search for project patterns and conventions
# General semantic search (project memory)
python memory/query.py "your question here" --agent-format

# Search only in architectural decisions
python memory/query.py "rate limiting" --type docs --agent-format

# Search in code
python memory/query.py "authentication middleware" --type code --agent-format

# Search in commits
python memory/query.py "fix deploy" --type git_commit --agent-format

# Search global cross-project memory
python memory/query.py "how did we solve auth" --global --agent-format

# Search both project + global, merged by relevance
python memory/query.py "rate limiting strategy" --both --agent-format

Always use --agent-format to get structured markdown output.

When to index

# After significant changes to docs/ or src/
python memory/index.py --incremental
# ADRs, post-mortems, and learner reports are auto-promoted to global memory
# if global_memory.enabled is true in config.yaml

Rules

  • ALWAYS check memory before creating an ADR (one may already exist on the topic)
  • ALWAYS check before implementing a complex feature
  • If memory returns relevant context, CITE the source in the implementation plan
  • If no results, move on without mentioning memory

Setup (if not configured)

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 · 57 lines · 52 tokens per session scan A 1e84b26122a7

Subscribe to this mod's changes

memory is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 425 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

project

Create or maintain an Architecture Studio project — initialize its record bundle, remember sourced facts, capture or supersede decisions, inspect project status, or migrate a 1.x PROJECT.md. Use when the user says “set up the project,” “remember this,” “we decided,” asks about project context, or runs /as:project.

AlpacaLabsLLC/skills-for-architects · 69 tokens

init-workspace-documentation

Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.

griddynamics/rosetta · 10 tokens

decision-memory

Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.

mbeacom/adrkit · 71 tokens

memory-continuity

Preserves cross-session continuity with deterministic MEMORY.md, index.md, and snapshot handoffs under .agentic/memories/.

soulcodex/agentic · 30 tokens

plan-memory-index

Maintains concise indexed memory entries for applied plans under .agentic/memories/ with clear boundaries between memory and plan sources. Memory retrieval is prioritized before loading historical plan files.

soulcodex/agentic · 40 tokens

self-improving-agent

Log learnings, errors, and corrections to .learnings/ for continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent, (3) A knowledge gap is identified, (4) A better approach is found. Captures corrections, insights, errors, and feature requests; promotes broadly…

mick-gsk/drift · 85 tokens