Plans Methodology
PassAudited by ClawScan on May 1, 2026.
Overview
This is an instruction-only planning methodology that stores plan documents in a workspace and does not request credentials, code execution, network access, or special permissions.
This skill appears safe to install for planning workflows. Before using it, make sure the workspace plans/ folder is a place where you are comfortable storing project context, approvals, and task history, and review active plans before letting an agent continue work from them.
Findings (1)
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.
Plan files may guide future agent behavior across sessions, so inaccurate or untrusted entries could cause the agent to continue the wrong work.
The skill intentionally reuses persistent plan files as context for future work, so stale or tampered plan documents could influence what the agent does next.
On Session Start 1. Check `plans/in_progress/` for active plans 2. Check `plans/draft/` for plans awaiting action 3. Continue where you left off
Keep the plans/ directory in a trusted workspace, review active and draft plans before relying on them, and record approvals clearly.