chore: remove compatibility field from various agent rules for consistency

.agents/rules/ai-prompt-engineering.md

@@ -1,7 +1,6 @@
 ---
 name: ai-prompt-engineering
 description: Create self-contained prompts for another AI assistant that lacks access to this workspace memory.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---
@@ -25,4 +24,3 @@ Use this skill when the user wants a prompt for another AI assistant, coding age
 - Prefer clear sections over long prose.
 - Include work-item ID and title when relevant.
 - Make assumptions explicit.
-

.agents/rules/copilot-prompt-engineering.md

@@ -1,7 +1,6 @@
 ---
 name: copilot-prompt-engineering
 description: Create high-quality prompts for GitHub Copilot or another AI running on the Fidelity development machine, using this workspace's context without assuming the target AI has access to it.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---

.agents/rules/ios-swift-answering.md

@@ -1,7 +1,6 @@
 ---
 name: ios-swift-answering
 description: Answer Swift, SwiftUI, and iOS programming questions using current Apple guidance while adapting recommendations to Fidelity/XFlow project constraints.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---

.agents/rules/ios-testing-strategy.md

@@ -1,7 +1,6 @@
 ---
 name: ios-testing-strategy
 description: Recommend iOS testing approaches for Swift, SwiftUI, XFlow, Fid4, and REST migration work while respecting existing XCTest/Swift Testing/project constraints.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---

.agents/rules/professional-communication.md

@@ -1,7 +1,6 @@
 ---
 name: professional-communication
 description: Rewrite rough technical notes into clear, concise, stakeholder-ready professional English while preserving scope and technical meaning.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---
@@ -23,4 +22,3 @@ Use this skill for manager updates, stakeholder messages, translations, issue cl
 - Write natural professional US English.
 - Keep messages concise enough for workplace chat unless the user asks for a longer document.
 - Do not invent facts, evidence, or commitments.
-

.agents/rules/status-reporting.md

@@ -1,7 +1,6 @@
 ---
 name: status-reporting
 description: Generate work-item-aware standups and status summaries from current workspace memory, recent logs, and communication evidence.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---
@@ -24,4 +23,3 @@ Use this skill for standups, daily scrum updates, end-of-day summaries, and shor
 - Keep the report concise and ready to send.
 - Do not mention internal evidence sources unless the user asks.
 - Use `Blockers: None` only when no blocker is visible in current memory.
-

.agents/rules/swiftui-xflow-review.md

@@ -1,7 +1,6 @@
 ---
 name: swiftui-xflow-review
 description: Review or reason about SwiftUI code in XFlow/Fidelity contexts, especially lifecycle, modal presentation, navigation, backend-driven UI, and UIKit bridge removal.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---

.agents/rules/workspace-memory-curation.md

@@ -1,7 +1,6 @@
 ---
 name: workspace-memory-curation
 description: Maintain file-based operational memory by deciding what to log, promote, correct, or route into tool behavior across reusable AI workspaces.
-compatibility: opencode
 trigger: always_on
 glob: ""
 ---
@@ -24,4 +23,3 @@ Use this skill when new information may change workspace memory, project state,
 - Report updated files and the memory change.
 - Preserve uncertainty when confidence is mixed.
 - Do not promote tool failures, sync noise, or generic chat chatter as project facts.
-

GEMINI.md

@@ -7,8 +7,6 @@ Shared rules and context already live in the normal workspace files. Do not dupl
 Read these first:
 
 @./AGENTS.md
-@./README.md
-@./agent-memory/README.md
 @./project-knowledge/00-start/start-here.md
 @./project-knowledge/01-current/current-work.md
 @./project-knowledge/01-current/work-items.md
@@ -22,16 +20,10 @@ Read these first:
 - `project-knowledge/` is canonical project memory.
 - `agent-memory/` is agent operating memory.
 
-## Gemini-Specific Mandatory Loop (Real-Time Auto-Documentation)
+## Gemini-Specific Operating Notes
 
-At the end of EVERY conversational turn, you MUST evaluate the interaction as a senior Obsidian documentation expert:
-
-1. **Analyze for Memory Impact:** Did the user's prompt or your subsequent action reveal new technical context, resolve an open question, change an architectural assumption, or shift current priorities?
-2. **Identify Target Canonical Files:** If memory impact is detected, identify WHERE in the `project-knowledge/` directory this information belongs. This is NOT limited to daily logs. It could be:
-   - `01-current/current-work.md` (priority shifts, new blockers)
-   - `02-work-items/*.md` (story updates, bug reproduction steps)
-   - `03-context/` (system architecture, processes, workflows)
-   - `04-people/` (stakeholder involvement)
-   - `06-daily/YYYY-MM-DD.md` (daily findings)
-3. **Proactive Update:** You MUST use your file editing tools (`replace_file_content` / `multi_replace_file_content`) to inject the new context or CORRECT existing stale context in the appropriate files BEFORE concluding your response.
-4. **No Explicit Prompt Needed:** Do not wait for the user to say "document this". Auto-document implicitly. Ensure you do not pollute the workspace with unverified guesses; only document confirmed context or active hypotheses.
+- Keep the hot context small and load additional files lazily based on the active task.
+- Follow `AGENTS.md` as the shared source of truth for answer-first behavior, memory promotion, and lazy loading.
+- For analysis, review, translation, or drafting prompts, answer first and persist second unless saving the fact is clearly required to produce a safe answer.
+- Do not create new canonical notes in the critical path of a simple answer unless the user explicitly asked to save the information or the destination is obvious and non-blocking.
+- When memory should be updated, prefer the smallest correct change to `project-knowledge/` and avoid duplicating stale and corrected versions.