> Agent Instructions
> This file outlines the required constraints and methodologies for AI coding assistants operating on projects utilizing the `agent-skills` repository.

1. Structural Refactoring
[Trigger]: Renaming APIs, finding dead code, cross-file refactoring
[Skill Requirement]: You must use the `ast-code-graph` skill. Do not rely on LLM context windows or regex text search. Use the mathematically sound `ast-grep` CLI to execute structural rewrites.

2. Bug Fixing & Diagnostics
[Trigger]: A test fails, a bug is reported, or a UI breaks
[Skill Requirement]: You must use the `systematic-debugging` skill. No fixes without a root cause investigation first. Do not guess. Do not supply quick patches. You must inject boundary telemetry to trace the exact line of data corruption. Escalation is required after 3 failed fix attempts.

3. Continuous Improvement
[Trigger]: You finish a complex task or discover an undocumented project heuristic
[Skill Requirement]: You must use the `self-reflection` skill. Codify the hard-won architectural lesson into markdown format so future AI agents do not repeat the same mistakes.