memory

memory is a skill for Claude Code from arozumenko/sdlc-skills. It costs 55 tokens per session (4,723 once invoked), scanned A, original, MIT.

A persistent memory system for coding agents that stores durable facts, preferences, decisions, and daily notes as plain Markdown files. Entries are organised by agent role and can be opened in Obsidian, a Markdown note-taking app.

In plain words
What is it for?
Remembering user preferences, project decisions, facts learned across sessions, and daily work logs.
Why use it?
It prevents useful information from being lost between sessions and keeps related notes findable through aliases and links. People can edit the files as well as the agent.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Gemini CLI.

Part of the sdlc-skills plugin — 53 skills shipped together

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

Made for: Claude Code.

Or install sdlc-skills, the plugin that ships this one along with the rest of its 53 skills.

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/arozumenko/sdlc-skills/memory.svg)](https://agentmods.dev/skills/arozumenko/sdlc-skills/memory)
Your own site
<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/memory"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,723 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 $0.00055 $0.04723
Opus 5 $0.00028 $0.02361
Sonnet 5 $0.00011 $0.00945
Haiku 4.5 $0.00006 $0.00472

Measured 6d ago against content hash 008e5882abf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/vault.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory

Persistent per-role memory as plain markdown. You — the agent — read and write these files directly using your Read, Write, Edit, and Glob tools. No CLI, no script, no shell-path fragility. Works on any host, from any working directory.

Write it as a vault, not a pile of notes. .agents/memory/<role>/ opens directly in Obsidian, so entries carry frontmatter properties, aliases, tags and [[wikilinks]]. That is not decoration: aliases make an entry findable by the words you would actually search for, links turn isolated facts into a graph you can follow, and the updated property tells you what is due for re-verification. A human may edit this vault too — tolerate keys you did not write; never strip them.

File layout

Under .agents/memory/<role>/ (where <role> matches your agent's name: frontmatter — e.g. project-manager, python-dev, scout):

.agents/memory/<role>/
├── MEMORY.md                ← index of the entries worth INJECTING (not all of them)
├── <slug>.md                ← individual curated entries (frontmatter + body);
│                              an entry may exist with no index line — that is normal
├── project_briefing.md      ← seeded by scout at install time (type: project)
├── daily/
│   └── YYYY-MM-DD.md        ← episodic daily logs, append-only
└── snapshot.md              ← host-generated convenience (often absent)

Create directories with mkdir -p on first use. Do not write snapshot.md yourself — a host launch hook may generate it, but nothing regenerates it automatically on every host. If it's absent, that's normal: you read memory directly when you need it.

.agents/ is an IDE-neutral path so the same memory works whether this agent is running under Claude Code, Cursor, Gemini CLI, Windsurf, or Copilot CLI.

Legacy paths (one-time migration)

If you find memory under one of these older locations and .agents/memory/<role>/ doesn't exist, migrate it before your first write:

Old location New location
.claude/memory/<role>/ (directory) .agents/memory/<role>/ — move the whole dir
.agents-legacy/memory/<role>/ (directory, older install) .agents/memory/<role>/ — move the whole dir
.claude/memory/<role>.md (flat file, from the former project-seeder skill) .agents/memory/<role>/project_briefing.md — wrap the existing content with type: project frontmatter (see "Write" op below) and add an index line — a project briefing is preventive by definition, so it earns one

Read the full file on GitHub · 395 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 395 lines · 55 tokens per session scan A 008e5882abf6

Subscribe to this mod's changes

memory is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 4,723 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens