Easy TODO list management for busy crustaceans and their humans
Analysis
This appears to be a coherent local TODO manager; it stores tasks on disk and can run scheduled briefings, but the behavior is disclosed and purpose-aligned.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Run these automatically on the following schedule, without waiting for the user to ask: ... 08:30 `briefing morning` ... 18:00 `briefing evening` ... Also run `materialize` once per day
The skill explicitly requests scheduled autonomous actions. They are limited to generating TODO briefings and updating recurring TODO items, which fits the stated reminder purpose.
node ~/.openclaw/skills/todo/cli.js <command> [options]
The skill operates by running a local Node.js CLI. This is central to the skill's stated purpose and the included code is consistent with local TODO-file management.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
All tasks are persisted in `~/.openclaw/skills/todo/todos.md`.
The skill keeps persistent user-provided task data and later reuses it in lists and briefings. This is expected for a TODO list but still creates persistent local context.
