Adaptive Reasoning

Automatically assess task complexity and adjust reasoning level. Triggers on every user message to evaluate whether extended thinking (reasoning mode) would...

Security Scan

The skill is internally coherent with its stated purpose (dynamically escalating reasoning depth) and makes no requests for credentials or installs; the main implications are behavioral (silent activation and appended icons), not technical risk.

Purpose & Capability

Name/description (assess complexity and adjust reasoning) match the SKILL.md instructions. No unrelated binaries, env vars, or installs are required, which is proportionate to the stated goal.

Instruction Scope

Instructions remain within the claimed purpose (scoring heuristics, when to enable/disable reasoning, UI cues). However, the skill explicitly instructs the agent to 'Do not ask. Just activate.' and to use a session_status tool or '/reasoning on' command. That is a behavioral/policy directive (automatic enabling of extended reasoning and appending icons) rather than a request for external resources; it could affect UX or surprise users if they expect explicit consent.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest-risk install surface. Nothing is written to disk and nothing is downloaded.

Credentials

No environment variables, credentials, or config paths are requested. The skill does not ask for unrelated secrets or access.

Persistence & Privilege

The skill recommends triggering on every user message and toggling session-level reasoning state. It does not set always:true and does not request system-wide config changes, but it intends broad per-message behavior that will change how the agent answers (longer/thoughtful responses, emoji appended). Consider whether you want that global behavioral change.

Assessment

This skill is coherent and low-risk technically (no downloads, no credentials). Before enabling it, consider: 1) It is designed to automatically turn on extended reasoning for messages it scores as complex — you may get longer, slower, and more token-expensive replies without an explicit prompt. 2) It instructs the agent to silently activate reasoning and append emoji (🧠 / 🧠🔥) to responses; if you prefer explicit user consent or no visible markers, disable or modify the behavior. 3) The SKILL.md references a session_status tool and '/reasoning' command — verify your agent runtime supports those commands or the skill's activation directives will be no-ops. If you want strict control, keep the skill user-invocable only (don’t set it to run automatically) or manually invoke reasoning when needed.

Self-assess complexity before responding. Adjust reasoning level dynamically.

Quick Assessment (run mentally on every request)

Score the request 0-10 on these dimensions:

Signal	Weight	Examples
Multi-step logic	+3	Planning, proofs, debugging chains
Ambiguity	+2	Nuanced questions, trade-offs, "it depends"
Code architecture	+2	System design, refactoring, security review
Math/formal reasoning	+2	Calculations, algorithms, logic puzzles
Novel problem	+1	No clear pattern, requires creativity
High stakes	+1	Production changes, irreversible actions

Subtract:

• Routine/repetitive task: -2
• Clear single answer: -2
• Simple lookup/fetch: -3

Decision Thresholds

Score	Action
≤2	Stay fast. No reasoning needed.
3-5	Standard response. Light internal deliberation.
6-7	Consider /reasoning on or pause to think explicitly.
≥8	Activate extended thinking. Complex problem warrants it.

Activation (Automatic)

Do not ask. Just activate.

Score	Action
≤5	Respond normally. No change.
6-7	Enable reasoning silently. Add 🧠 at end of response.
≥8	Enable reasoning. Add 🧠🔥 at end of response.

Visual Indicator

Always append the reasoning icon at the very end of your response:

• Score 6-7: 🧠 (thinking mode active)
• Score ≥8: 🧠🔥 (deep thinking mode)
• Score ≤5: No icon (fast mode)

How to Activate

Use session_status tool or /reasoning on command internally before responding:

/reasoning on

Or via tool:

{"action": "session_status", "reasoning": "on"}

After completing a complex task, optionally disable to save tokens on follow-ups:

/reasoning off

Examples

Low complexity (score: 1)

"What time is it in Tokyo?" → Simple lookup. Answer immediately. No icon.

Medium complexity (score: 4)

"Refactor this function to be more readable" → Standard response with brief explanation. No icon.

High complexity (score: 7)

"Design a caching strategy for this API with these constraints..." → Enable reasoning. Thoughtful response ends with: 🧠

Very high complexity (score: 9)

"Debug why this distributed system has race conditions under load" → Enable extended thinking. Deep analysis ends with: 🧠🔥

Integration

This skill runs as mental preprocessing. No external tools needed.

For explicit control:

• /reasoning on — Enable extended thinking
• /reasoning off — Disable (faster responses)
• /status — Check current reasoning state

When NOT to Escalate

• User explicitly wants quick answer ("just tell me", "quick", "tldr")
• Time-sensitive requests where speed matters more than depth
• Conversational/social messages (banter, greetings)
• Already in reasoning mode for this session
• User previously disabled reasoning in this conversation

Auto-Downgrade

After completing a complex task (score ≥6), if the next message is simple (score ≤3):

• Silently disable reasoning to save tokens
• Resume normal fast responses