openclaw-memory

openclaw-memory is a skill for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 68 tokens per session (1,952 once invoked), scanned A, original, MIT.

A four-layer memory setup for OpenClaw agents, using permanent instruction files, short-lived daily logs, session transcripts, and a searchable retrieval index. OpenClaw is an agent system, but the supplied information does not explain its wider purpose.

In plain words
What is it for?
Use it to set up agent memory files and daily logs, configure shared memory and retrieval, and diagnose why an agent cannot recall earlier information.
Why use it?
It addresses common memory failures: information that was never saved, details lost during context summarization, and important notes removed when memory is reduced.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions AGENTS.md; built for openclaw.

Part of the openclaw plugin — 31 skills, 22 commands, 4 agents, 3 hooks shipped together

Good fit Use it to set up agent memory files and daily logs, configure shared memory and retrieval, and diagnose why an agent cannot recall earlier information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory
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.

Any agent
npx skills add TheophilusChinomona/claude-openclaw-plugin --skill openclaw-memory
Clone the repo
git clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-plugin

Made for: Claude Code.

Or install openclaw, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 4 agents, 3 hooks.

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 openclaw-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory/github.svg)](https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory)
Your own site
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for openclaw-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,952 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00068 $0.01952
Opus 5 $0.00034 $0.00976
Sonnet 5 $0.00014 $0.00390
Haiku 4.5 $0.00007 $0.00195

Measured 10d ago against content hash 401c387eb1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

openclaw-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 10d 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.

plugins/openclaw/skills/openclaw-memory/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Memory Architecture (OpenClaw)

Memory is the most fragile part of an agent system. Three failure modes kill agent memory:

  1. Never stored — the agent saw it but never persisted it
  2. Compaction destroyed it — context compaction summarized away the detail
  3. Pruning trimmed it — MEMORY.md grew past budget and lost the entry

This skill teaches the four-layer memory model, bootstrap file setup, shared memory patterns, and defenses against each failure mode.

The Four Memory Layers

Layer Name Persistence Scope Example
1 Bootstrap files Permanent (committed) Per-agent AGENTS.md, SOUL.md, MEMORY.md
1.5 Daily logs Semi-permanent (7-14 days) Per-agent memory/2026-03-10.md
2 Session transcript Temporary (session lifetime) Per-session ~/.openclaw/agents//sessions/*.jsonl
3 Retrieval index Permanent (vector DB) System-wide ~/.openclaw/memory/lancedb/

See references/memory-layers.md for deep dives on each layer including token budgets, eviction order, and LanceDB setup.

Bootstrap Files (Layer 1)

Every agent workspace should contain these files, loaded at session start:

File Purpose Loaded When Sub-agent Visibility
AGENTS.md Operating manual, safety rules, delegation rules Always (first) Yes — essential rules here
SOUL.md Personality, boundaries, communication style Always No (main agent only)
IDENTITY.md Name, role, avatar, vibe Always No
USER.md User profile, preferences, timezone Private sessions only No
MEMORY.md Long-term curated knowledge (200-line budget) Private sessions only No
TOOLS.md Available tools, integration notes On demand Yes
HEARTBEAT.md Proactive monitoring checklist On heartbeat cron No

Sub-agent visibility rule: Sub-agents only receive AGENTS.md + TOOLS.md. Keep essential safety rules in AGENTS.md, not SOUL.md.

Read the full file on GitHub · 183 lines

Files

What ships with it

2 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. 10d ago First seen · 183 lines · 68 tokens per session scan A 401c387eb1eb

Subscribe to this mod's changes

openclaw-memory is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 1,952 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 2026-08-31.

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

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

shellm

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

laude-institute/headlong · 49 tokens