feat(skills): add operating-modes skill (#385)

[ashp15205]

Summary

Adds a new operating-modes skill to the registry that addresses the context collapse problem described in Issue #385.

Closes #385

What This Adds

A new skill at skills/operating-modes/ with 4 triggers:

Trigger	Mode	Behavior
/mode:builder	🚀 Builder	Ship fast. Minimal ceremony. One feature at a time.
/mode:maintainer	🛠 Maintainer	Stability first. Surgical diffs. Zero surprises.
/mode:architect	🏛 Architect	No code. Plans, trade-offs, decision records only.
/mode:economy	⚡ Economy	Token-aware. Minimal context. Changed lines only.

How It Works

When a user invokes a mode trigger (e.g. /mode:maintainer), the skill injects a structured set of behavioral constraints into the agent's system prompt — preventing the agent from:

• Refactoring unbroken code (Maintainer)
• Writing code before architecture is decided (Architect)
• Reading unnecessary files (Economy)
• Over-engineering features (Builder)

Source & Validation

These mode prompts have been battle-tested in the Vibe Coding Essentials open-source repository. They are the result of real-world iteration against multiple LLMs (GPT-4o, Claude Sonnet, Qwen3) across dozens of development sessions.

Files Changed

• skills/operating-modes/SKILL.md — [NEW] Agent-facing skill definition with YAML frontmatter and mode instructions
• skills/operating-modes/README.md — [NEW] Human-facing notes, usage examples, and mode transition guide

Testing

Manually validated that:

• Each trigger is unique and non-conflicting with existing skills
• YAML frontmatter follows the existing SKILL.md schema (name, description, triggers)
• All 4 modes produce distinct, non-overlapping behavioral constraints

[all-hands-bot]

👋 This PR needs a couple of things fixed before OpenHands can review it:

• the PR description's HUMAN: section needs at least 20 characters describing what you tested, not just the template placeholder

Push an update once this is addressed and this check re-runs automatically.

This is an automated check - no AI was used to generate this comment.

[all-hands-bot]

👋 This PR needs a couple of things fixed before OpenHands can review it:

• the PR description's HUMAN: section needs at least 20 characters describing what you tested, not just the template placeholder

Push an update once this is addressed and this check re-runs automatically.

This is an automated check - no AI was used to generate this comment.

[all-hands-bot]

👋 This PR needs a couple of things fixed before OpenHands can review it:

• the PR description's HUMAN: section needs at least 20 characters describing what you tested, not just the template placeholder

Push an update once this is addressed and this check re-runs automatically.

This is an automated check - no AI was used to generate this comment.

[all-hands-bot]

👋 This PR needs a couple of things fixed before OpenHands can review it:

• the PR description's HUMAN: section needs at least 20 characters describing what you tested, not just the template placeholder

Push an update once this is addressed and this check re-runs automatically.

This is an automated check - no AI was used to generate this comment.