gsd-fast

Execute trivial tasks inline without subagents or planning steps.

Updated May 21, 2026
One-click install
npx skills add https://github.com/jedmamosto/m-and-ms --skill gsd-fast-jedmamosto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd-fast
Source: https://github.com/jedmamosto/m-and-ms/tree/main/.agents/skills/gsd-fast
Command: npx skills add https://github.com/jedmamosto/m-and-ms --skill gsd-fast-jedmamosto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes friction for tiny, one-shot tasks by letting you execute work immediately in the current context without setting up planning or subagents.

Core Features & Use Cases

  • Inline execution: Runs the requested work directly without spawning subagents.
  • Low overhead changes: Suited for quick edits like typo fixes, small config tweaks, small refactors, or adding missing files/lines.
  • End-to-end for micro-tasks: Handles the full completion loop for tasks that fit in a single short instruction.

Quick Start

Ask the skill to fix a specific typo in the given file path and apply the smallest safe edit needed to correct it.

Frequently Asked Questions about gsd-fast

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I execute a quick edit inline without spawning subagents?

To execute a quick edit inline without subagents, request the task directly in your current context. The system applies the smallest safe edit end-to-end, bypassing planning steps and subagent overhead for trivial changes.

What is the best way to apply a typo fix or config change without generating a plan file?

The best way to apply a typo fix or config change without a plan file is using inline execution. It handles micro-tasks end-to-end immediately, skipping PLAN.md generation and subagent setup for one-shot edits.

Can I do a micro-refactor directly in the current context for a small bash script?

Yes, you can do a micro-refactor directly in the current context for a small bash script. This approach processes small refactors instantly without subagent overhead, applying changes end-to-end within the fast workflow.

When should I avoid inline execution for repo maintenance tasks?

You should avoid inline execution for repo maintenance tasks that require multi-step planning or complex refactoring. This approach is strictly suited for one-shot, low overhead changes like typo fixes, config tweaks, or forgotten commits.

Does inline execution work for adding missing lines to a file without setting up subagents?

Yes, inline execution works for adding missing lines to a file without subagents. It runs the requested work directly in the provided fast workflow context, completing small additions end-to-end without planning overhead.