A skill that sets up a long-term memory system for a project. It creates a memory file for decisions and a folder for supporting details, then adds instructions to CLAUDE.md.

Use it to initialize project memory, or check whether the system is already set up before deciding whether to initialize it again.

Important project decisions can be lost between coding sessions. A shared memory file gives the agent a place to retain the project's focus, blockers, open items, and history.

ltm:init — Skill for Claude Code and Codex by LaserPhaser: A skill that sets up a long-term memory system…

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/laserphaser/claude-ltm/ltm-init

Any agent

npx skills add LaserPhaser/claude-ltm --skill ltm-init

Clone the repo

git clone --depth 1 https://github.com/LaserPhaser/claude-ltm

Made for: Claude Code, Codex.

Or install claude-ltm, the plugin that ships this one along with the rest of its 3 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/laserphaser/claude-ltm/ltm-init.svg)](https://agentmods.dev/skills/laserphaser/claude-ltm/ltm-init)

Your own site

<a href="https://agentmods.dev/skills/laserphaser/claude-ltm/ltm-init"><img src="https://agentmods.dev/badge/skills/laserphaser/claude-ltm/ltm-init.svg" alt="Measured on agentmods" height="20"></a>

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 692 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.

Model	Per session	Once invoked
Fable 5	$0.00018	$0.00692
Opus 5	$0.00009	$0.00346
Sonnet 5	$0.00004	$0.00138
Haiku 4.5	$0.00002	$0.00069

Measured 4d ago against content hash a6c78c3c85ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ltm:init 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 4d 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/ltm-init/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Long-Term Memory

Set up the claude-ltm memory system in this project.

What to do

Check if .memory/DECISIONS.md already exists. If it does, inform the user that LTM is already initialized and ask if they want to re-initialize (which will update CLAUDE.md instructions but NOT overwrite existing decisions).

Create the following structure:

.memory/
├── DECISIONS.md    (empty memory with Status + Changelog scaffolding)
└── details/        (empty directory for future detail files)

Create .memory/DECISIONS.md with this content:

# Project Memory

> Auto-maintained by claude-ltm. Last updated: YYYY-MM-DD

## Status
- **Focus**:
- **Blockers**: None
- **Open**:

## Changelog

Add the LTM instructions section to the project's CLAUDE.md. If CLAUDE.md doesn't exist, create it. If it exists, append the LTM section at the end. Do NOT duplicate if  already exists.

The instructions to add (wrapped in markers for clean uninstall):

<!-- BEGIN claude-ltm -->
# Long-Term Memory (claude-ltm)

You have a project decision memory at `.memory/DECISIONS.md`. This file is the
team's persistent record of significant decisions made during development.

## At session start
- Read `.memory/DECISIONS.md` to understand prior decisions and current status.

## During work
- When you make or discover a significant decision (architecture, tech stack,
  changed approach, business logic, resolved debate), update `.memory/DECISIONS.md`
  immediately.
- "Significant" = something a teammate joining next week would need to know.
  Routine code changes are NOT decisions. Choosing a database IS.
- Each entry gets a ### heading with [date], up to ~10 lines of context.
- If a decision is truly complex (>10 lines), create a detail file in
  `.memory/details/YYYY-MM-DD-<topic>.md` and link to it.
- When a prior decision is superseded, update its entry in-place. Note what
  changed and why. Update the Changelog section.
- Check for duplicates before adding — update existing entries, don't repeat.

## Before finishing your session
- Do a compact pass: review this session's work and check if any decisions
  were made but not yet recorded in `.memory/DECISIONS.md`.
- Update the Status section (current focus, blockers, open questions).
- Skip if nothing significant was decided.
<!-- END claude-ltm -->

Read the full file on GitHub · 80 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.

4d ago First seen · 80 lines · 18 tokens per session scan A a6c78c3c85ab

Subscribe to this mod's changes

ltm:init is a skill published in the GitHub repository LaserPhaser/claude-ltm (4 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 692 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.

Memory and context claude-code claude-plugin claude-skill long-term-memory

memory-map

Two-tier project memory system. Maintains a global Claude memory snapshot of all ongoing projects AND a per-project STATUS.md file in each project folder that captures last-session state, next actions, blockers, and key locations — so context survives long absences. Operates in two modes. WRITE mode triggers when the…

shandar/memory-map · 215 tokens

memory-prune

Clean stale, outdated, or redundant entries from Claude's stored memory. Use this skill when the user says things like "clean up memory", "prune memory", "memory is getting cluttered", "remove old entries", "consolidate memory", or "trim the memory map". Also trigger proactively when memory approaches its limits — 30…

shandar/memory-map · 147 tokens

memory-recall

Load and summarise stored project memory at the start of a session, or whenever the user asks what Claude remembers about their work. Use this skill when the user says things like "what do you remember", "what's the context", "where did we leave off", "catch me up", "what's the current state", "show me the memory…

shandar/memory-map · 156 tokens

ltm:init