Decision Topology

PassAudited by ClawScan on May 1, 2026.

Overview

This appears to be a local, purpose-aligned conversation-structure logger, but it creates persistent local memory files that users should manage deliberately.

Install this only if you want an always-available local record of how conversations branch and evolve. Review the configured trees directory periodically, avoid recording highly sensitive topics if that is a concern, and set always: false if you want recording to happen only on request.

Findings (2)

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.

What this means

Your brainstorming structure, short summaries, rejected ideas, and concepts may be saved locally and reused to connect future conversations.

Why it was flagged

The skill intentionally creates persistent local memory artifacts and cross-tree links from conversation-derived summaries and concepts.

Skill content
Concept indexing — cross-tree linking via keyword concepts
- Companion .md files — auto-generated for semantic search indexing
Recommendation

Treat the trees directory as sensitive local memory. Review, move, or delete tree files if a conversation contains private or confidential topics.

What this means

The agent may update local topology files during brainstorming or problem-solving without interrupting the conversation.

Why it was flagged

The skill is designed for always-on, low-noise recording during relevant conversations, so users may not see a message each time a local node is written.

Skill content
Active by default... Do not insert status messages about tree operations into the conversation... Think: git commits in the background.
Recommendation

If you prefer explicit control, change the skill metadata to always: false or invoke it only when you want a conversation topology recorded.