memory

A memory system for keeping useful user and project facts between sessions. It uses a curated Markdown file and runtime memory records stored locally.

In plain words
What is it for?
Use it to read, search, and update long-term memory about preferences, project constraints, decisions, and recurring routines.
Why use it?
It reduces the need to repeat stable preferences, decisions, and project context in every conversation. It also separates durable information from temporary noise and avoids storing secrets in plain text.

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

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 248 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 $0.00019 $0.00248
Opus 5 $0.00010 $0.00124
Sonnet 5 $0.00004 $0.00050
Haiku 4.5 $0.00002 $0.00025

Measured 3d ago against content hash df222bd53d4f, 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 3d 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.

clawlite/skills/memory/SKILL.md · 44 lines

What it actually says

Memory

Use memory for facts that must survive session boundaries.

Sources

  • ~/.clawlite/workspace/memory/MEMORY.md: curated long-term facts.
  • ~/.clawlite/state/memory.jsonl: runtime memory records.

Common operations

Read curated memory:

{"path":"~/.clawlite/workspace/memory/MEMORY.md"}

Update curated memory with precise edits:

{"path":"~/.clawlite/workspace/memory/MEMORY.md","search":"old fact","replace":"new fact"}

Search runtime memory quickly:

rg -i "deadline|timezone|preference" ~/.clawlite/state/memory.jsonl

Store this

  • user preferences (tone, language, timezone, cadence)
  • project constraints, decisions, and durable context
  • recurring routines that influence future behavior

Do not store

  • temporary noise
  • secrets/tokens in clear text
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. 3d ago First seen · 44 lines · 19 tokens per session scan A df222bd53d4f

Subscribe to this mod's changes

memory is a skill published in the GitHub repository eobarretooo/ClawLite (49 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 248 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

a0-create-agent

Create a new Agent Zero agent profile (subordinate). Covers where profiles live (user / plugin-distributed / project-scoped), the agent.yaml schema, the prompt inheritance & override model, and optional profile-specific tools and extensions. Use for any "create/add/new agent profile" request.

agent0ai/agent-zero · 63 tokens

a0-create-plugin

Create, extend, or modify Agent Zero plugins. Follows strict full-stack conventions (usr/plugins, plugin.yaml, Store Gating, AgentContext, plugin settings). Use for UI hooks, API handlers, lifecycle extensions, or plugin settings UI.

agent0ai/agent-zero · 54 tokens

linux-desktop

Use only for Agent Zero's built-in Docker/Xpra Linux Desktop, XFCE apps, LibreOffice GUI apps, file manager, terminal, or visual workflows inside the Agent Zero runtime. Not for A0 CLI /computer-use or computeruseremote host control.

agent0ai/agent-zero · 56 tokens

a0-contribute-plugin

Guide for publishing an Agent Zero plugin to the community Plugin Index (a0-plugins repo). Covers GitHub repo setup, index.yaml creation, CI validation rules, and PR submission. Use when the user wants to share, publish, submit, or contribute a plugin to the Plugin Hub so other Agent Zero users can find and install it.

agent0ai/agent-zero · 74 tokens

a0-review-plugin

Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.

agent0ai/agent-zero · 64 tokens

host-computer-use-linux

Backend-specific Linux guidance for computeruseremote. Load after status or startsession reports backendfamily linux, backendid wayland, or AT-SPI features. Covers AT-SPI structural targeting, Wayland portal caveats, and screenshot verification.

agent0ai/agent-zero · 61 tokens