mcpField
R
reasoning-controls

reasoning-controls

github.com/nickcrewAgent workflows6277 installsUpdated 17w ago
Repository

About reasoning-controls

A skill for setting reasoning depth, budget limits, and metrics in tasks that need explicit reasoning controls. It uses task-specific references to guide configuration and reporting of settings and effects.

Key features

  1. 01Adjust reasoning depth
  2. 02Set cost or latency budgets
  3. 03Report reasoning metrics
  4. 04Use focused reference guides

Use cases

  1. 01Tune thinking depth for a task
  2. 02Limit reasoning cost or latency
  3. 03Report reasoning settings and metrics

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nickcrew/claude-cortex --skill reasoning-controls

After installing, type/reasoning-controlsin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
adjust.md
budget.md
metrics.md

Details

From the project README

Reasoning Controls

Overview

Control reasoning depth and cost trade-offs using consistent settings and metrics.

When to Use

  • Adjusting reasoning depth or thinking mode
  • Setting budget limits for cost or latency
  • Reporting reasoning metrics

Avoid when:

  • The task doesn’t require explicit reasoning controls

Quick Reference

TaskLoad reference
Adjust reasoningskills/reasoning-controls/references/adjust.md
Budget controlsskills/reasoning-controls/references/budget.md
Metrics reportingskills/reasoning-controls/references/metrics.md

Workflow

  1. Determine the control goal (depth, budget, metrics).
  2. Load the matching reference.
  3. Apply the control with the appropriate parameters.
  4. Report settings and effects.

Output

  • Updated reasoning settings
  • Metrics or confirmation output

Common Mistakes

  • Over-allocating budget for simple tasks
  • Changing depth without explaining trade-offs

Comments

Markdown supported