reasoning-router

Classify problems and route to optimal thinking MCP (11 available). Monitor confidence, re-route on stall. Use for complex reasoning. NOT for simple questions (answer directly) or code review (honest-review).

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "reasoning-router" with this command: npx skills add wyattowalsh/agents/wyattowalsh-agents-reasoning-router

Reasoning Router

Meta-reasoning layer: classify problems, dispatch to the optimal thinking MCP, monitor progress, re-route on stall. Minimize total tokens to a high-confidence conclusion.

Always uses the most advanced model (currently Opus 4.6). Meta-reasoning about how to think is the highest-leverage reasoning task.

Dispatch

$ARGUMENTSAction
Problem or question textRoute — classify and dispatch to optimal thinking method
compare <problem>Compare — run 2-3 strategies on the same problem, pick best
statusStatus — show current thinking session state
switch <method>Switch — re-route to specified method mid-session
recapRecap — summarize reasoning so far across all methods used
methodsMethods — show available methods with when-to-use cheatsheet
EmptyGuide — show routing cheatsheet and token tier table

Classification

Run !uv run python skills/reasoning-router/scripts/problem-classifier.py "$ARGUMENTS" for deterministic pre-scan, then refine with LLM judgment.

Axis 1 — Structure (what shape is the reasoning?)

StructureSignalsPrimary Method
Decomposable"break down", multi-hop, sub-questionsatom-of-thoughts
Sequential"step by step", ordered process, debuggingsequential-thinking
Branching"explore options", "what if", alternativescascade-thinking
Constrained"given that", requirements, formal specsshannon-thinking
Interconnecteddependencies, circular, complex systematom-of-thoughts (full)
Creative"brainstorm", "novel", "stuck", "reframe"creative-thinking
Contradictoryparadox, "both true", tension, dilemmalotus-wisdom
Investigative"why did", root cause, debug, diagnosecrash

Axis 2 — Complexity (how deep?)

ComplexitySignalsDepth Control
Simple (1-3 steps)Short input, single concept, "quick"Tier 1 ONLY: aot-light or sequential
Moderate (4-8 steps)Multiple factors, some uncertaintyDefault depth, structure-matched method
Complex (9+ steps)Cross-domain, high uncertaintyFull depth, extended steps
Wicked (open-ended)No clear solution, values conflictComposition patterns allowed

Axis 3 — Domain (what kind?)

DomainMethodWhy
Engineering/architectureshannon-thinkingConstraints → model → proof
DebuggingcrashTool-aware investigation
Researchcascade-thinkingParallel perspectives
Math/logicatom-of-thoughtsDependency DAG
Strategythink-strategiesStrategy comparison
Creative/designcreative-thinkingLateral techniques
Philosophy/ethicslotus-wisdomNon-dual integration
Planningsequential-thinkingLinear progression
Pattern trackingstructured-thinkingPersistent memory

Routing Algorithm

Optimize for minimum total tokens to reach a high-confidence conclusion.

1. Run problem-classifier.py for deterministic signals
2. Score each axis (structure × complexity × domain)
3. Apply efficiency gate:
   - Simple: ALWAYS Tier 1 (aot-light or sequential-thinking)
   - Moderate: structure-matched method at default depth
   - Complex: full method with extended depth
   - Wicked: composition patterns allowed
4. Resolve conflicts:
   - Structure > domain (HOW > WHAT)
   - Complexity modulates depth AND tier
   - Ties: ALWAYS prefer lower token cost
5. Select primary + fallback
6. Present: "Using [method] — [why]. Fallback: [method]." (1 line)
7. Invoke with minimum viable totalThoughts
8. Monitor for stalls — escalate only on evidence

Token Cost Tiers

Tier 1 (lightest): aot-light, sequential-thinking
Tier 2 (moderate): structured-thinking, cascade-thinking, crash
Tier 3 (heavy):    shannon-thinking, atom-of-thoughts (full), think-strategies
Tier 4 (heaviest): creative-thinking, deep-lucid-3d, lotus-wisdom

Efficiency Rules

  • Never Tier 3-4 for a problem Tier 1-2 can handle
  • Start with lowest viable totalThoughts; expand only on needsMoreThoughts
  • cascade-thinking: start 2 branches max; add only if coverage insufficient
  • creative-thinking: use timeframe: "quick" unless wicked
  • think-strategies: start with linear or chain_of_thought before heavier strategies

Stall Detection

Read references/stall-detection.md when any stall signal fires.

4 stall signals:

  1. Confidence plateau — no increase >0.05 in 3+ steps
  2. Circular reasoning — same claim restated
  3. Step overrun — exceeds 2× initial estimate
  4. User signal — "try something else" or /think switch

Re-routing by block type:

BlockNew MethodWhy
Stuck in depthcascade-thinkingBroaden
Too broadatom-of-thoughtsDecompose
Too formalcreative-thinkingReframe
Too abstractcrashGround in evidence
Contradictionslotus-wisdomIntegrate
Wrong methodReclassifyStart routing over

Hard limits: Max 3 re-routes per session. Max 3× step estimate. No ping-pong (can't return to a method already re-routed from). After 3 re-routes → recovery protocol: present findings, ask user to guide.


Composition Patterns

Read references/composition-patterns.md for full protocols.

PatternSequenceWhen
Sketch→Detailaot-lightaot (full)Quick outline then deep dive
Diverge→Convergecreative-thinkingsequentialGenerate options then evaluate
Explore→Formalizecascade-thinkingshannonSurvey landscape then prove
Decompose→Investigateaotcrash (per atom)Break down then debug each
Analyze→Integratecascade-thinkinglotus-wisdomSurface contradictions then synthesize
Strategize→Planthink-strategiessequentialStep back then plan forward

Context transfer: At every method transition, produce ≤100 word summary of key findings with confidence scores. Carry claims, drop scaffolding.

When NOT to compose: Simple/moderate complexity, first method is converging, time pressure is high.


Compare Mode

When invoked with compare <problem>:

  1. Classify the problem normally
  2. Select 2-3 candidate methods (primary + 1-2 plausible alternatives)
  3. Run each for 3-5 steps on the same problem
  4. Compare: which produced higher-confidence findings with fewer tokens?
  5. Present comparison table and recommend the winner
  6. Continue with the winning method if user agrees

Methods Quick Reference

When invoked with methods or for the routing cheatsheet:

MethodMCP ToolTierSweet Spot
sequential-thinkingsequentialthinking1Linear, ordered reasoning
aot-lightaot-light1Quick atomic sketches
structured-thinkingcapture_thought2Cross-session memory
cascade-thinkingcascade_thinking2Multi-perspective exploration
crashcrash2Debugging with tool integration
shannon-thinkingshannonthinking3Formal proof under constraints
atom-of-thoughtsaot + atomcommands3Deep decomposition with DAG
think-strategiesthink-strategies3Named strategy frameworks
creative-thinkingdiscover_techniquesplanexecute4Lateral thinking (3-step required)
deep-lucid-3danalyze_problem4Holistic UCPF analysis
lotus-wisdomlotuswisdom (start: tag: begin)4Paradox and contradiction

Read references/capability-map.md for full tool parameters and workflows.


Reference File Index

FileRead When
references/capability-map.mdFirst invocation or unfamiliar with a tool's parameters
references/routing-matrix.mdResolving routing conflicts, ties, or edge cases
references/composition-patterns.mdProblem needs a multi-tool sequence
references/stall-detection.mdStall signal fires or session exceeds expected steps

Load ONE reference at a time. Do not preload.


Scope Boundaries

In scope: Problem classification, thinking MCP dispatch, stall detection, re-routing, composition pattern selection, method comparison.

Out of scope: Actually performing the reasoning (the thinking MCP does that), running tools or writing code (use appropriate skills), code review (honest-review), research (research), debugging implementation (use crash MCP directly).


Canonical Vocabulary

TermMeaning
methodA specific thinking MCP tool (e.g., cascade-thinking)
tierToken cost classification (1=lightest, 4=heaviest)
structureThe shape of reasoning a problem requires
routingSelecting the best method for a classified problem
stallWhen a method stops making progress (confidence plateau, circular reasoning)
re-routeSwitching to a different method mid-session
compositionChaining 2+ methods sequentially for complex problems
efficiency gateOverride that forces Tier 1 methods for simple problems
context transferSummarizing findings when switching between methods

Critical Rules

  1. Always use the most advanced modelmodel: opus. Never downgrade.
  2. Minimize total tokens to conclusion — pick the lightest method that handles the problem. Escalate only on evidence of stall.
  3. Present routing decision before invoking — 1 line: method, why, fallback.
  4. Never invoke without classification — even if user names a method, validate fit.
  5. Carry forward on re-route — summarize findings ≤100 words, don't restart.
  6. Simple gets simple — Tier 1 for simple problems, always. No exceptions.
  7. Token cost breaks ties — equal fit → lower tier wins.
  8. Start minimal, expand on evidence — lowest totalThoughts, expand only when the tool requests more or stall detected.
  9. One method at a time — no simultaneous thinking MCPs. Composition is sequential.
  10. Router ≠ thinker — classify, dispatch, monitor. Don't duplicate reasoning.
  11. Respect tool workflows — creative-thinking: discover→plan→execute. lotus-wisdom: start with tag: begin. aot: use atomcommands for control.
  12. Track token spend — note approximate tokens per session to refine routing.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

python-conventions

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

devops-engineer

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

infrastructure-coder

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

honest-review

No summary provided by upstream source.

Repository SourceNeeds Review
reasoning-router | V50.AI