PlanSuite
v0.1.3Create, finalize, and execute file-based project plans with subplans, using checkpoints and logs for controlled, session-based implementation and progress tr...
⭐ 1· 2.3k·8 current·8 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
There is no separate description in registry metadata, but the SKILL.md clearly defines a file-based planning/execution workflow (task_plan.md, progress.md, findings.md). The resources it requires (none) and actions it prescribes (create/update local files) are consistent with a planning tool. Minor note: source/homepage are unknown and the top-level registry description is missing, which reduces provenance but does not make the behavior incoherent.
Instruction Scope
Instructions are tightly scoped to creating and updating three files in the current working directory, enforcing a freeze/execute workflow, and recommending use of an isolated session (sessions_spawn) for execution. There are no instructions to read unrelated system files, access external endpoints, or exfiltrate data. The guidance to 'do not paste these three files into chat' simply enforces file-based persistence.
Install Mechanism
No install spec and no code files — this is instruction-only, so nothing will be downloaded or written by an installer. Lowest risk per install mechanism.
Credentials
No environment variables, credentials, or config paths are requested. The instructions only require permission to create/update files in the current working directory, which is proportional to a file-based planning workflow.
Persistence & Privilege
The skill does not request 'always: true' or other elevated persistence. It only instructs the agent to write three files in the working directory and to spawn an isolated session for execution — this is normal for a project-run workflow and does not modify other skills or global agent configuration.
Assessment
This skill is a local, file-based planning workflow and appears coherent: it creates/updates task_plan.md, progress.md, and findings.md in whichever working directory the agent runs in. Before installing or invoking it: (1) understand the agent will write to your current working directory — back up or run in an empty/sandbox directory if you care about file safety; (2) avoid putting secrets or sensitive credentials into the plan files; (3) note the registry metadata lacks a homepage/description and the source is unknown — if provenance matters to you, prefer skills with clear authorship; (4) check whether your agent platform’s sessions_spawn (isolated session) capability is available and behaves as you expect. Other than those operational cautions, the skill's requests and instructions are proportionate to its stated planning purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk973e2sjmdf9wqty8mq5sagnpn80jn2g
License
MIT-0
Free to use, modify, and redistribute. No attribution required.