feat: Update behavior rules and documentation for workspace maintenance and flow references

knowledge/agent-memory-rules.md

@@ -59,6 +59,23 @@ Do not ask the user what to promote unless the ambiguity is real and material.
 
 ---
 
+## Tooling Self-Maintenance
+
+User corrections about how the workspace should behave are memory-worthy when they affect future output.
+
+If a correction applies to a command, prompt, skill, agent, or reusable rule, update the linked tool directly instead of only logging the correction.
+
+Examples:
+
+- A standup formatting correction should update `prompts/standup.md` and `.opencode/commands/standup.md`.
+- A Mattermost freshness correction should update the Mattermost command/plugin instructions.
+- A Copilot prompt-structure correction should update `prompts/copilot-prompt.md`, `.opencode/commands/copilot-prompt.md`, or the Copilot skill.
+- A Swift answer-quality correction should update the relevant iOS skill or `ai/context/ios/` guidance.
+
+Keep the daily log as evidence of what happened, but make the reusable behavior live in the file that controls that behavior.
+
+---
+
 ## File Selection
 
 ### `ai/logs/YYYY-MM-DD.md`
@@ -119,6 +136,18 @@ When the role is not explicit, store:
 
 Use for explicit confirmed decisions with ongoing impact.
 
+### `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.opencode/skills/`, and `knowledge/`
+
+Use these when the new information changes how the workspace should operate:
+
+- command invocation behavior
+- reusable output format
+- default agent behavior
+- specialized skill workflow
+- persistent process or memory rules
+
+Do not create a separate note when an existing command, prompt, agent, or skill is the source of truth.
+
 ---
 
 ## What Not To Store