Adaptive Reasoning
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent and low risk, but it will automatically toggle reasoning mode and change response formatting during a session.
This skill appears safe for users who want the agent to decide when to think more deeply. Be aware that it may enable reasoning automatically, affect response speed or token usage, and add icons to responses.
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.
The agent may silently use deeper reasoning, potentially changing latency, token use, and response style, and may append reasoning icons to answers.
The skill instructs the agent to automatically invoke internal reasoning controls without asking the user each time. This is aligned with the skill’s purpose, but it changes session behavior automatically.
Do not ask. Just activate. ... Use `session_status` tool or `/reasoning on` command internally before responding
Install only if you want automatic reasoning-mode adjustment; otherwise prefer manual `/reasoning on` and `/reasoning off` control.