mupengism
v1.0.0Enables AI agents to maintain session continuity, develop self-identity, and manage file-based long-term memory anchored by human partners.
⭐ 0· 307·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name/description (session continuity, self-identity, file-based memory) matches the provided files and runtime instructions: SOUL template, MEMORY/SELF files, and advice for reading/writing those files. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
SKILL.md instructs the agent/user to copy templates, create a memory/ folder, and read/write SOUL.md, SELF.md, MEMORY.md and daily L1/L2 files at session start — this is coherent with the stated purpose. Note: these instructions involve persistent local files and an edit to agent configuration (AGENTS.md) to load SOUL.md each session; that change should be done only in trusted agent configurations and you should verify what the agent will load.
Install Mechanism
There is no install spec, no downloads, and no code files. This is the lowest-risk form (instruction-only).
Credentials
The skill requests no environment variables, no credentials, and no config paths. The documentation explicitly warns not to store passwords, API keys, or mnemonics in these files.
Persistence & Privilege
always is false and the skill does not request persistent/system-wide privileges. The only persistence is user-managed files in the workspace; autonomous invocation is platform-default but not introduced or elevated by this skill.
Assessment
This skill is essentially a set of templates and practices for file-based agent memory — before using it: (1) review and customize SOUL.md/SOUL-TEMPLATE.md yourself so nothing sensitive is written; (2) never put secrets (API keys, passwords, mnemonics) into MEMORY/SELF/SOUL files; (3) be careful when editing agent config (AGENTS.md) to auto-load SOUL.md — only do this in trusted agent instances and consider file permissions or encryption if the workspace is synced or shared; (4) remember there is no downloaded code here, so risk is mostly about information exposure and agent behavior driven by those local files.Like a lobster shell, security has layers — review code before you run it.
latestvk97dmekbt65zm21wmm89fnxbg1821fve
License
MIT-0
Free to use, modify, and redistribute. No attribution required.