memclaw-maintance
v0.9.31MemClaw Maintenance Guide — Installation, configuration, and maintenance guidance. For daily usage and tool operations, use the [`memclaw` skill](https://cla...
⭐ 1· 139·0 current·0 all-time
by@sopaco
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the content: the skill is an installation/configuration/maintenance guide for MemClaw. All actions described (install plugin, enable plugin, configure LLM/embedding keys, migrate local memories, run maintenance commands) are coherent with a maintenance role. Nothing in the files asks for unrelated cloud provider credentials or unrelated system-wide access.
Instruction Scope
The SKILL.md instructs the agent/admin to edit openclaw.json / AGENTS.md and to run migration that reads local memory files (~/.openclaw/workspace/memory/) and to call MemClaw runtime endpoints (cortex_* calls). Those actions are expected for migration/maintenance but are capable of reading local memory files and changing agent behavior (the guide insists on making the agent load persistent memory at conversation start). Users should be aware migration reads local files and that modifying AGENTS.md affects agent startup behavior.
Install Mechanism
This skill contains no install spec or code — it is instruction-only. It tells the user to run the OpenClaw CLI to install @memclaw/memclaw, and points to a GitHub repository. The skill itself does not automatically download or execute code, so the installation risk is delegated to the plugin installation step (not part of this skill bundle).
Credentials
The skill does not declare environment variables, but instructs configuring LLM and embedding API keys in OpenClaw plugin settings (llmApiKey, embeddingApiKey, base URLs, models). These are proportionate to a memory/embedding plugin, but users should confirm API keys are only for their intended LLM/embedding providers and understand they will be stored in OpenClaw config (marked sensitive).
Persistence & Privilege
The skill does not request 'always: true' or special privileges. It does instruct persistent changes to agent configuration (AGENTS.md / openclaw.json) so the MemClaw behavior becomes a default; that is expected for a maintenance guide but is effectively a persistent change to agent behavior and should be reviewed before applying.
Assessment
This is an instruction-only maintenance guide and appears internally consistent, but before proceeding: 1) Verify the authenticity of the @memclaw/memclaw plugin and the referenced GitHub repo (review its code and releases) because the plugin installation will fetch and run code on your machine. 2) Backup your existing OpenClaw workspace (~/.openclaw/workspace) before running migration; migration reads and converts local memory files. 3) Be deliberate when editing AGENTS.md/openclaw.json: the guide recommends making MemClaw the default memory path and always loading persistent memory at conversation start, which changes agent behavior. 4) Ensure the LLM and embedding API keys you enter are for the intended providers and keep them secret; the guide says keys are stored as sensitive but confirm your OpenClaw config practices. 5) Check port usage (6333, 6334, 8085) and firewall rules if the plugin auto-starts services. If you want to reduce risk, inspect the plugin package source before installing and test on a non-production environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk977k0tq63qk36qy2m5076k4a984098t
License
MIT-0
Free to use, modify, and redistribute. No attribution required.