Agent skill

Leviathan Memory

by elstongun in elstongun/leviathan

Long-term memory across sessions with the Leviathan memory store.

Apache-2.0Auto-check passedAgent Workflows

Install Leviathan Memory

skills CLI
$ npx skills add elstongun/leviathan --skill leviathan-memory -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install elstongun/leviathan leviathan-memory --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/elstongun/leviathan.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/leviathan-memory .claude/skills/leviathan-memory && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
leviathan-memory
GitHub stars
716
Token cost
~799 tokens
SKILL.md length
270 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Long-term memory across sessions with the Leviathan memory store.

  • Tasks that involve Agent memory
  • SKILL.md covers Start of a session, Before acting, Remember and Correct and forget, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Leviathan Memory is an agent skill from elstongun/leviathan. Long-term memory across sessions with the Leviathan memory store. Use at the start of a session to recall what is known about the user, the project and past decisions; before acting on anything you may have learned before (preferences, conventions, owners, deploy steps, past failures); and whenever you learn something durable that a later session should know, or the user says "remember", "from now on", "I prefer", "we decided", or corrects an earlier fact.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent memory. The repository describes itself as: Deep memory for agents over large datasets. Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or anything a database CLI can export) into… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Agent memory

Example prompts

  • “remember”
  • “from now on”
  • “I prefer”
  • “/leviathan-memory”

What it can do on your machine

Read from SKILL.md and the folder at commit f1070fe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Leviathan Memory loads about 799 tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 270 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~119
When it runs · the whole SKILL.md, loaded when a task matches
~799

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from elstongun/leviathan at commit f1070fe, republished under its Apache-2.0 licence (© elstongun). 270 words, ~799 tokens.

Download SKILL.mdSave it as .claude/skills/leviathan-memory/SKILL.md (or your agent's skills folder).
name
leviathan-memory
description
Long-term memory across sessions with the Leviathan memory store. Use at the start of a session to recall what is known about the user, the project and past decisions; before acting on anything you may have learned before (preferences, conventions, owners, deploy steps, past failures); and whenever you learn something durable that a later session should know, or the user says "remember", "from now on", "I prefer", "we decided", or corrects an earlier fact.

Leviathan memory: remember once, recall in a few tokens

The leviathan memory CLI is a small database of claims, one per row. A recall returns only what fits a token budget, current values first, so it stays cheap however much has been remembered. If the recall and remember MCP tools are available, use them instead; they take the same arguments.

Start of a session

bash
leviathan memory recall                     # the briefing: pinned and important memories across subjects

Before acting

bash
leviathan memory recall <words as the user said them>
leviathan memory recall -s <subject>        # everything current about a person, project or service
leviathan memory recall --kind decision,lesson deploy

An empty answer means not remembered, not untrue. Try other words or a subject, or ask the user.

Remember

bash
leviathan memory remember "Prefers pnpm over npm" --kind preference -s josh -k package_manager
leviathan memory remember "Deploys go through staging first, after the March outage" --kind decision -s deploys -k path -i 4
leviathan memory remember "The flaky auth test fails when run before the cache warms" --kind lesson -s auth-tests
  • One claim per call, in one sentence, in words a later question would use.
  • Anything that can change gets a subject (-s) and a key (-k). Writing the same subject and key again replaces the old value; that is how corrections work. Don't write a second, contradicting memory without the key.
  • Decisions carry their reason. Lessons say what to do differently.
  • Remember durable things: preferences, conventions, decisions, owners, environments, recurring failures. Not the conversation, not things the code or git history already shows, not one-off details of the current task.
  • --importance 5 or --pin only for what every session must know.
  • Never store secrets. They are refused (exit 2). Remember where a secret lives, not its value.

The reply says whether the memory was new, merged with a restatement, or replaced an older value, and lists related memories. If a related one is now wrong, forget it or overwrite its key.

Correct and forget

bash
leviathan memory forget <id> --reason "moved to yarn"
leviathan memory forget -s josh -k package_manager
leviathan memory history -s josh -k package_manager    # every value the slot has had
leviathan memory recall --as-of 2025-06 deploy          # what was true then

Store

The default store is ~/.leviathan/memory.db; --memory=PATH or LEVIATHAN_MEMORY picks another, and --ns separates projects. Add --json for structured output. Exit codes: 0 ok, 1 error, 2 refused or bad request.

© elstongun, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/leviathan-memory of elstongun/leviathan.

Open the folder on GitHubat commit f1070fe

Compare with similar skills

Leviathan Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Leviathan Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Leviathan Memory this skillelstongun/leviathan716—~799Automated safety check: PassApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Beads Task Memorygastownhall/beads28k—~1.2kAutomated safety check: PassMIT
Reflect on Session Learningscursor/plugins11k5 repos~1.2kAutomated safety check: PassNone
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT
Compound Learning WriterEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT

Similar skills

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed
  • Beads Task Memory

    gastownhall/beads

    Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.

    28k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Official

    Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.

    11k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

    24k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from elstongun/leviathan

  • Leviathan

    elstongun/leviathan

    Search a large indexed dataset (tickets, logs, incidents, maintenance records, orders, notes, any table or export) and get a few ranked, cited records instead of reading raw data.

    716 GitHub stars~887 tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Leviathan Memory

What does Leviathan Memory do?

Long-term memory across sessions with the Leviathan memory store. Leviathan Memory is an agent skill from elstongun/leviathan. Long-term memory across sessions with the Leviathan memory store.

When should I use Leviathan Memory?

Leviathan Memory fits situations like: tasks that involve Agent memory.

How do I install Leviathan Memory in Claude Code?

Run `npx skills add elstongun/leviathan --skill leviathan-memory -a claude-code`. Or copy the skill folder (skills/leviathan-memory in elstongun/leviathan) into .claude/skills/leviathan-memory in your project. Claude Code loads it when a task matches its description.

How do I install Leviathan Memory in Codex?

Run `npx skills add elstongun/leviathan --skill leviathan-memory -a codex`. Or copy the skill folder (skills/leviathan-memory in elstongun/leviathan) into .agents/skills/leviathan-memory in your project. Codex loads it when a task matches its description.

Can I use Leviathan Memory in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add elstongun/leviathan --skill leviathan-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/leviathan-memory, .gemini/skills/leviathan-memory, .github/skills/leviathan-memory and .opencode/skills/leviathan-memory in your project.

What does Leviathan Memory need to run?

SKILL.md names no scripts, command-line tools or credentials: Leviathan Memory is instructions for the agent only.

Does Leviathan Memory access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Leviathan Memory safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Leviathan Memory use?

Leviathan Memory is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Leviathan Memory use?

About 799 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Leviathan Memory?

Skills that share tags, products or a category with Leviathan Memory: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Beads Task Memory (gastownhall/beads, 28k stars), Reflect on Session Learnings (cursor/plugins, 11k stars) and MemPalace Memory Search (MemPalace/mempalace, 59k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Leviathan Memory?

elstongun (a GitHub user) maintains it in elstongun/leviathan, which has 716 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 9, 2026.

Source: elstongun/leviathan on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.