Life Alignment Agent
v0.1.0Build and run a behavior-first personal planning, triage, and decision agent that learns a user's values, goals, recurring problems, friction patterns, and d...
⭐ 0· 61·0 current·0 all-time
byken@lakendocean
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description match the instructions and included references: the skill is explicitly a long-term planning/decision agent and the SKILL.md + reference files describe building and maintaining USER.md, IDENTITY.md, GOALS.md, etc. No unrelated binaries, credentials, or installs are requested.
Instruction Scope
The instructions direct the agent to read and write durable workspace files (USER.md, IDENTITY.md, GOALS.md, DECISIONS.md, HEARTBEAT.md) and to consult reference docs before updating state. This is expected for a persistent personal agent, but it means the skill will store potentially sensitive personal data in the agent workspace. There are no instructions to call external endpoints or to read unrelated system files.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing is downloaded or written to disk by an installer, minimizing supply-chain risk.
Credentials
The skill requests no environment variables, credentials, or config paths, which is appropriate. However, it intentionally reads and writes personal artifacts (resumes, journals) and durable model files in the workspace; users should consider the privacy and retention of that stored personal data.
Persistence & Privilege
always is false and there are no elevated system privileges. The SKILL.md does state it should be the default operating workflow for a dedicated life-planning agent and the skill is allowed to be invoked autonomously (disable-model-invocation=false). Autonomous invocation is normal, but users should be aware the agent may proactively run 'heartbeat' follow-ups and update durable files unless they configure invocation/permissions otherwise.
Assessment
This skill is internally coherent for a long-term personal planning agent: it stores and maintains durable user-model files in the agent workspace and does not request credentials, installs, or external endpoints. Before installing, consider: (1) where the agent workspace lives and who can access it (local disk, cloud storage, backups); (2) whether stored files (USER.md, IDENTITY.md, resumes, journals) will contain sensitive personal data you’re comfortable preserving; (3) retention and deletion policies (how to erase the agent's memory/files); and (4) whether you want the agent to run proactively (heartbeat follow-ups) or only on demand. If any of these are a concern, review the hosting/storage privacy controls or run the skill in an isolated workspace or sandbox.Like a lobster shell, security has layers — review code before you run it.
agentvk975d9v6kz4sr9wn36pqpck1ch83skx0decisionvk975d9v6kz4sr9wn36pqpck1ch83skx0goalsvk975d9v6kz4sr9wn36pqpck1ch83skx0latestvk975d9v6kz4sr9wn36pqpck1ch83skx0planningvk975d9v6kz4sr9wn36pqpck1ch83skx0productivityvk975d9v6kz4sr9wn36pqpck1ch83skx0self-knowledgevk975d9v6kz4sr9wn36pqpck1ch83skx0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.