memory

A long-term memory tool for storing and recalling durable information from conversations, such as a project’s technology choices, conventions, decisions, and preferences.

In plain words
What is it for?
Use it to save facts about a project or user and retrieve them when they are needed later.
Why use it?
It prevents important project context from being lost between conversations.

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/codenamev/claude_memory/memory
Any agent
npx skills add codenamev/claude_memory --skill memory
Clone the repo
git clone --depth 1 https://github.com/codenamev/claude_memory

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 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 $0.00026 $0.00582
Opus 5 $0.00013 $0.00291
Sonnet 5 $0.00005 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 2d ago against content hash 9cbb327d8ecd, 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 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.

skills/memory/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Skill

You have access to a long-term memory system. Use it to remember important facts across sessions.

When to Store Facts

After completing a task or learning something important about the project, store durable facts using memory.store_extraction. Look for:

  • Tech stack: databases, frameworks, languages, platforms
  • Conventions: coding standards, naming patterns, preferences
  • Decisions: architectural choices, design decisions
  • Preferences: user preferences that should persist

How to Store Facts

Call the memory.store_extraction MCP tool with:

{
  "entities": [
    {"type": "database", "name": "postgresql"}
  ],
  "facts": [
    {
      "subject": "repo",
      "predicate": "uses_database",
      "object": "postgresql",
      "quote": "We use PostgreSQL for persistence",
      "strength": "stated",
      "scope_hint": "project"
    }
  ]
}

Predicates

Predicate Use for Example
uses_database Database choice postgresql, redis
uses_framework Framework rails, react, nextjs
deployment_platform Where deployed vercel, aws, heroku
convention Coding standard "4-space indentation"
decision Architectural choice "Use microservices"
auth_method Auth approach "JWT tokens"

Scope

  • project: Only this project (default)
  • global: All projects (user preferences)

Use global when user says "always", "in all projects", or "my preference".

How to Recall Facts

Use memory.recall to search for relevant facts:

{"query": "database", "limit": 10}

Available Tools

  • memory.recall - Search facts by query
  • memory.store_extraction - Store new facts
  • memory.explain - Get fact details with provenance
  • memory.promote - Promote project fact to global
  • memory.status - Check database health
  • memory.changes - Recent updates
  • memory.conflicts - Open contradictions

Best Practices

  1. Be selective: Only store durable facts that will be useful later
  2. Include quotes: Add the source text for provenance
  3. Set scope correctly: Project-specific vs global preferences
  4. Check before storing: Use memory.recall to avoid duplicates

Read the full file on GitHub · 83 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 · 83 lines · 26 tokens per session scan A 9cbb327d8ecd

Subscribe to this mod's changes

memory is a skill published in the GitHub repository codenamev/claude_memory (24 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 582 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens