Proactive Tasks
v1.2.3Proactive goal and task management system. Use when managing goals, breaking down projects into tasks, tracking progress, or working autonomously on objectives. Enables agents to work proactively during heartbeats, message humans with updates, and make progress without waiting for prompts.
⭐ 10· 3.8k·13 current·13 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (proactive task management) match what the package does: CLI to create goals/tasks, select next task, log progress, and run health checks. The files and functions (tasks.json, WAL, SESSION-STATE.md, working-buffer) are proportionate to the stated purpose. No unrelated env vars, binaries, or cloud credentials are requested.
Instruction Scope
SKILL.md instructs the agent to run the included Python CLI and to create/append/read files in the workspace (memory/, SESSION-STATE.md, working-buffer). That is expected for persistent task management, but the docs also encourage cron/heartbeat patterns and autonomous messaging ('message human on completion/blocker'), so operators should be aware this skill is designed to persist state on disk and to operate autonomously (send updates) when enabled.
Install Mechanism
No install spec; it's an instruction-only/embedded-script skill. No remote downloads, package registry installs, or external installers were observed. This minimizes install-time code risk.
Credentials
The skill declares no environment variables or credentials. The code does not attempt to read env vars or external credentials. It writes limits its file access to skill-local data/ plus workspace memory files, which is proportionate to its purpose.
Persistence & Privilege
The skill persists data (data/tasks.json) and writes WAL, working-buffer, and SESSION-STATE.md under the workspace memory directory. It is not force-included (always:false). This persistence is expected for the functionality but means logs and session-state files will be created on disk and could contain task content — review file permissions and retention policies before enabling autonomous runs.
Assessment
This package appears internally consistent for a proactive task manager, but review a few operational details before installing:
- File writes: the script will create/update data/tasks.json, memory/WAL-YYYY-MM-DD.log, memory/working-buffer.md, and SESSION-STATE.md in your workspace. Ensure those locations are acceptable (no sensitive secrets) and set file permissions/retention accordingly.
- Autonomous behavior: SKILL.md recommends cron/heartbeat patterns and autonomous 'isolated agentTurn' runs that may message humans. Confirm you want the agent to run background jobs and send updates automatically; restrict or review messaging targets in your environment.
- Configuration placeholders: docs reference a person name ('Imran') and example cron commands—replace placeholders with your own targets and verify the paths (/openclaw, openclaw-runner) match your runtime.
- Origin and versions: repository/homepage are not authoritative here (source unknown, package.json/README versions vary). If you need a higher trust level, request the upstream source or authorship verification and review the full scripts before granting autonomous operation.
If you allow autonomous invocation, run the code in a controlled environment first and inspect created files to confirm no unexpected data is being recorded or transmitted.Like a lobster shell, security has layers — review code before you run it.
latestvk970kzdt2w30w11w4hh4t5xp9s810rb3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.