PlanSuite

Create, finalize, and execute file-based project plans with subplans, using checkpoints and logs for controlled, session-based implementation and progress tr...

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.

Type: OpenClaw Skill Name: plansuite Version: 0.1.3 The OpenClaw AgentSkills skill bundle defines a structured workflow for an AI agent to manage projects, including planning, freezing, and executing tasks. The `SKILL.md` instructions are clear, aligned with the stated purpose, and notably include a recommendation to use `sessions_spawn` for isolated execution, which is a strong security-conscious instruction. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts to subvert the agent, or obfuscation. All file operations are confined to creating and updating specific markdown files (`task_plan.md`, `progress.md`, `findings.md`) within the working directory, which is consistent with its stated purpose.