ohc-coding-discipline

Enforce minimal-scope coding with explicit assumptions and verifiable success criteria.

2|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/iadr-dev/colab --skill ohc-coding-discipline
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ohc-coding-discipline
Source: https://github.com/iadr-dev/colab/tree/main/skills/ohc-coding-discipline
Command: npx skills add https://github.com/iadr-dev/colab --skill ohc-coding-discipline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill prevents AI coding work from drifting into overengineering by forcing explicit assumptions, minimal scope, clean diffs, and evidence-based success criteria.

Core Features & Use Cases

  • Explicit assumptions: states interpretations and asks when ambiguity could cause large work or risky outcomes.
  • Minimal scope + scope guard: avoids speculative features, refactoring, and unrelated fixes; logs out-of-scope issues to the notepad.
  • Surgical changes + goal-driven execution: keeps diffs tied to the request, defines “done” with verifiable criteria, and verifies by reading verification output.
  • Team handoff discipline: updates the notepad with done/blocked/gotchas and writes for collaborators.
  • Workflow gates for larger tasks: enforces plan presence for tasks estimated over 30 minutes and runs a scope-check after finishing.

Quick Start

Ask your agent to apply "ohc-coding-discipline" while implementing a code change, including writing explicit success criteria and verifying by reading test/output evidence.

Frequently Asked Questions about ohc-coding-discipline

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

FAQPage Schema
How do I prevent AI coding agents from overengineering and drifting scope during refactoring?

To prevent AI coding agents from overengineering during refactoring, enforce explicit assumptions, minimal scope, and surgical diffs tied to the request. Log out-of-scope issues to a handoff notepad instead of speculative fixes.

How do I define verifiable success criteria for code review and bug fixes?

Define verifiable success criteria for code review and bug fixes by requiring evidence-based verification. Read actual test and output verification data to confirm completion, rather than relying on assumptions or unverifiable claims.

Does this workflow require a plan for larger code changes estimated over 30 minutes?

Yes, workflow gates enforce plan presence for tasks estimated over 30 minutes. After finishing, a scope-check script runs to verify the actual code changes remained surgical and within the defined boundaries.

How do I handle ambiguity before modifying a codebase with an AI agent?

Handle ambiguity before modifying a codebase by forcing explicit assumptions. State interpretations upfront and ask clarifying questions when ambiguity could cause large work efforts or risky outcomes.

What is the best way to manage team handoff after AI agent code changes?

Manage team handoff after AI agent code changes by updating a dedicated notepad. Document completed work, blocked items, and gotchas specifically for collaborators to maintain clear communication.