Add instruction altitude guidance and context engineering reference

[eanders-tdy]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services. N/A — no paid services involved.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

Adds guidance on instruction altitude (the Goldilocks zone for writing effective instructions) to instructions/instructions.instructions.md.

The addition includes:

• A new "Instruction Altitude (Goldilocks Zone)" subsection under Content Guidelines with three actionable principles and a summary table showing the three altitude levels (over-specified, under-specified, right altitude) and their failure modes.
• A new "Hypothetical-rule inflation" entry under Patterns to Avoid, discouraging rules added for failures that have not actually occurred.
• An updated resource link pointing to Anthropic's Effective Context Engineering for AI Agents article, scoped to the system-prompt altitude section that is directly relevant to instruction files.

These additions are grounded in Anthropic's published guidance on system prompt design and help contributors write instruction files that are specific enough to guide behavior without becoming brittle.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.
• Other (please specify):

---

Additional Notes

The "right altitude" concept is sourced from Anthropic's Effective Context Engineering for AI Agents, specifically the section on system prompt design. The full article also covers tool design, compaction, and sub-agent architectures — topics more relevant to agent files — so only the instruction-file-relevant portion is referenced here.

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[Copilot]

Pull request overview

Updates the repository’s instruction authoring guidance by adding “instruction altitude” (right-sizing specificity) recommendations and refining anti-patterns/resources to help contributors write more effective, resilient instruction files.

Changes:

• Added an “Instruction Altitude (Goldilocks Zone)” subsection with actionable principles and a summary table.
• Added a new “Hypothetical-rule inflation” anti-pattern under “Patterns to Avoid”.
• Updated the “Additional Resources” list with a context-engineering reference link.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.