Plans & Todos
v1.0.0管理长期规划与短期待办事项。当用户提到目标、任务、计划、路线图，或需要将复杂目标拆解为存储在 memory/plans-todos.md 中的可执行项时使用。
⭐ 0· 278·0 current·0 all-time
byInfiniEcho@dawnlck
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the instructions: the skill records, decomposes, queries, and updates plans/todos stored in ~/.openclaw/workspace/memory/plans-todos.md. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
Instructions are limited to reading/writing the specified local file and creating the containing directory if missing, which is appropriate. Note: the skill's guidance encourages proactive behavior (e.g., auto-creating Plans and auto-updating tasks when the user mentions completion), which may result in edits to the file without explicit confirmation — this is functional but could be surprising to some users.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk by an installer and there are no external downloads.
Credentials
No environment variables, credentials, or unrelated config paths are requested. The only resource used is a single local file under the user's OpenClaw workspace, which fits the stated purpose.
Persistence & Privilege
always:false and normal model invocation are used (no forced/global inclusion). The skill will create and persist a local file and directory in the user's workspace and may autonomously update it per its instructions — this is expected but worth noting as a data persistence behavior.
Assessment
This skill appears coherent and only interacts with a single local file (~/.openclaw/workspace/memory/plans-todos.md). Before installing, consider: 1) Are you comfortable the agent will create and update that file and may proactively add or mark tasks based on conversation? If not, require explicit confirmation before writes. 2) Don’t store secrets in Plans (the skill already warns this). 3) Check file permissions and backups if the content is sensitive. 4) If you use cloud sync for your workspace, be aware that stored plans will be included in that sync. If any of these are unacceptable, avoid enabling autonomous updates or instruct the agent to ask before making changes.Like a lobster shell, security has layers — review code before you run it.
latestvk973yh6b6medtv16pb1pftzzmd82kp5a
License
MIT-0
Free to use, modify, and redistribute. No attribution required.