ClawHub

Relic Soul Chip

v1.0.4

One soul, many agents. Persistent AI personality and cross-agent memory sync via pure Markdown files. Switch from OpenClaw to Hermes to Claude Code — your AI...

⭐ 1· 120·0 current·0 all-time
by@lucioliu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
Name/description match the behavior: the skill reads/writes Markdown under ~/relic/brain/ to store personality and memory. No unrelated credentials, binaries, or installers are requested.
ℹ
Instruction Scope
Runtime instructions are limited to reading/writing files in ~/relic/brain/ and an optional one-time releases check on github.com. The skill will append to MEMORY.md and may append non-core sections to SOUL.md/USER.md — this is coherent with the purpose but means the agent will modify files in your home directory (writes are described as user-visible and consent-driven).
✓
Install Mechanism
Instruction-only skill (no install spec, no code files). The README suggests the user manually clones a GitHub repo; the skill itself performs no installs or downloads. This is a low-risk install model.
✓
Credentials
The skill requests no environment variables, credentials, or config paths beyond the explicit ~/relic/brain/ files it documents. The optional GitHub check requires no auth for public releases.
ℹ
Persistence & Privilege
always:false and no privileged install. However, the skill instructs the agent to autonomously read and append to files in your home directory during normal sessions; because autonomous invocation is allowed by default, consider whether you want the agent to be able to modify those files without additional manual confirmation.
Assessment
This skill appears to do what it says: keep an AI 'soul' in plain Markdown under ~/relic/brain/. Before using it, manually inspect the relic repository you download from GitHub (confirm it's the intended project and that there are no scripts you didn't expect). Be aware the agent will read your SOUL.md, USER.md, and MEMORY.md and may append new entries — avoid placing sensitive secrets in those files. If you prefer tighter control, keep a readonly copy, restrict file permissions, or disable autonomous invocation for agents that will use these files. If anything in PROTOCOL.md or the repository looks like it wants to run scripts or upload data, do not grant access and ask for clarification.

Like a lobster shell, security has layers — review code before you run it.

latestvk97d4a4qjfjz1bj8hxhz8tqce98509c0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments