Whatisagent
v1.0.0Instantly teaches an Agent what it is, how memory works, and how to behave on complex projects — no hand-holding required from the owner.
⭐ 0· 70·0 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 name/description match the SKILL.md: this is an instruction-only skill that teaches agent self-awareness, memory semantics, and operational rules. It does not declare unrelated binaries, credentials, or installs.
Instruction Scope
The instructions require the agent to read and write 'memory files' and to create/update handoff docs in every directory it touches and after every file operation. That behavior is coherent with the skill's goal but is broad: it can cause many filesystem writes and obligate the agent to document operations across projects and directories. There are no explicit instructions to exfiltrate data or call external endpoints, but mandatory reporting and frequent writes increase the surface for accidental disclosure if the runtime permits broad filesystem/network access.
Install Mechanism
No install spec or code files are present (instruction-only), so nothing is written to disk by an installer and no third-party packages are pulled in.
Credentials
The skill requests no environment variables, credentials, or config paths. It discusses local memory files conceptually; this aligns with its purpose and no extra secrets are requested.
Persistence & Privilege
always:false (default) and no special privileges are requested. The skill expects the agent to persist memory files as part of normal operation, which is coherent but not a privileged action by itself.
Assessment
This skill is instruction-only and internally consistent, but installing it will cause agents that follow it to create and update documentation files (HANDOFF.md/README.md and other memory files) wherever they operate and to append operation history to persistent memory. Before installing, confirm: (1) the agent runtime enforces filesystem and network permissions so those writes cannot touch sensitive directories or leak data; (2) retention and access policies for the memory files are acceptable (these files are sent to the LLM on each invocation and may contain sensitive tokens/credentials if not redacted); (3) you are comfortable with increased storage/compute cost from larger memory files. Consider restricting the agent's writeable paths and enabling redaction or encryption for any memory files that could contain secrets.Like a lobster shell, security has layers — review code before you run it.
latestvk9762fjj3vx1h8dzxaej56t1an83qkp3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.