Memory Integrity Checker

Community

ArchieIndian

memory-integrity-checker

Validates memory summary DAGs for structural integrity — detects orphan nodes, circular references, token inflation, broken lineage, and stale summaries that corrupt the agent's memory.

Overview

Publisher	ArchieIndian
Repository	`openclaw-superpowers`
Skill name	`memory-integrity-checker`
Stars	74
Forks	14
Bundled files	3
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by ArchieIndian on GitHub. Read the source before you install it.

Installation

Install the Memory Integrity Checker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/ArchieIndian/openclaw-superpowers/tree/main/skills/openclaw-native/memory-integrity-checker
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/ArchieIndian/openclaw-superpowers/tree/main/skills/openclaw-native/memory-integrity-checker

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers.git /tmp/openclaw-superpowers
mkdir -p .claude/skills
cp -r /tmp/openclaw-superpowers/skills/openclaw-native/memory-integrity-checker .claude/skills/memory-integrity-checker

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Memory Integrity Checker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Memory Integrity Checker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Memory Integrity Checker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Memory Integrity Checker

What it does

As memory DAGs grow through compaction, they can develop structural problems: orphan nodes with no parent, circular reference loops, summaries that inflated instead of compressing, broken lineage chains, and stale nodes that should have been dissolved. These problems silently corrupt the agent's memory.

Memory Integrity Checker runs 8 structural checks on the DAG, generates a repair plan, and optionally auto-fixes safe issues.

Inspired by lossless-claw's DAG integrity checking system, which detects and repairs corrupted summaries.

When to invoke

Automatically Sundays at 3am (cron) — weekly structural audit
After a crash or unexpected shutdown — check for corruption
When the agent's memory seems inconsistent — diagnose structural issues
Before a major compaction or prune operation — ensure clean starting state

Integrity checks (8 total)

Check	What it detects	Severity
ORPHAN_NODE	Node with no parent and not a root	HIGH
CIRCULAR_REF	Circular parent-child loops in the DAG	CRITICAL
TOKEN_INFLATION	Summary has more tokens than its combined children	HIGH
BROKEN_LINEAGE	Edge references a node ID that doesn't exist	CRITICAL
STALE_ACTIVE	Active node older than 30 days with no children	MEDIUM
EMPTY_NODE	Node with empty or whitespace-only content	HIGH
DUPLICATE_EDGE	Same parent-child edge appears multiple times	LOW
DEPTH_MISMATCH	Node's depth doesn't match its position in the DAG	MEDIUM

How to use

bash
python3 integrity.py --check                  # Run all 8 integrity checks
python3 integrity.py --check --fix            # Auto-fix safe issues
python3 integrity.py --check --only ORPHAN_NODE  # Run a specific check
python3 integrity.py --repair-plan            # Generate repair plan without fixing
python3 integrity.py --status                 # Last check summary
python3 integrity.py --format json            # Machine-readable output

Procedure

Step 1 — Run integrity checks

bash
python3 integrity.py --check

Runs all 8 checks and reports findings by severity.

Step 2 — Review repair plan

bash
python3 integrity.py --repair-plan

For each finding, shows what the auto-fix would do:

ORPHAN_NODE → reattach to nearest active root or deactivate
DUPLICATE_EDGE → remove duplicates
EMPTY_NODE → deactivate
STALE_ACTIVE → deactivate

Step 3 — Apply safe fixes

bash
python3 integrity.py --check --fix

Auto-fixes LOW and MEDIUM severity issues. HIGH and CRITICAL require manual review.

State

Check results, finding history, and repair actions stored in ~/.openclaw/skill-state/memory-integrity-checker/state.yaml.

Fields: last_check_at, findings, check_history, repairs_applied.

Notes

Reads from memory-dag-compactor's state file — does not maintain its own DAG
Auto-fix only applies to LOW and MEDIUM severity issues
CRITICAL issues (circular refs, broken lineage) require manual intervention
Circular reference detection uses DFS with visited-set tracking
Token inflation check compares parent tokens vs. sum of children tokens

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Memory Integrity Checker AI skill do?

Validates memory summary DAGs for structural integrity — detects orphan nodes, circular references, token inflation, broken lineage, and stale summaries that corrupt the agent's memory.

Why use Memory Integrity Checker on TypingMind?

Because you install it once and use it with any model. Memory Integrity Checker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Memory Integrity Checker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ArchieIndian/openclaw-superpowers/tree/main/skills/openclaw-native/memory-integrity-checker. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Memory Integrity Checker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Memory Integrity Checker?

As many as you like. As long as a model supports skills, you can use Memory Integrity Checker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Memory Integrity Checker AI skill free?

It is published on GitHub by ArchieIndian. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Release Openclaw Maintainer

openclaw

OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

Release Openclaw Plugin Testing

openclaw

OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Auto Qa

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Memory Integrity Checker

What it does

When to invoke

Integrity checks (8 total)

How to use

Procedure

State

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now