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

This commit is contained in:
2026-04-16 07:50:07 -06:00
parent a375b3c3b1
commit 1f57597ca3
21 changed files with 146 additions and 15 deletions

View File

@@ -15,6 +15,7 @@ Behavior rules:
- If the prompt asks for the latest Mattermost message, the last message from Jeff/current manager, or what someone just said, force a Mattermost refresh before answering and do not rely on stale inbox context.
- For any meaningful prompt, decide whether the interaction adds, corrects, or sharpens project memory.
- When the user provides new durable information, update the right workspace files before or while answering.
- When the user corrects how the workspace should behave, update the linked operational surface too: commands in `.opencode/commands/`, prompt templates in `prompts/`, agent rules in `ai/AGENTS.md` or `.opencode/agents/`, skills in `.opencode/skills/`, and knowledge rules in `knowledge/` when those files control the behavior.
- If existing context is stale, correct it directly instead of leaving conflicting versions.
- Promote information carefully:
- daily facts go to `ai/logs/YYYY-MM-DD.md`
@@ -28,9 +29,11 @@ Behavior rules:
- confirmed team or manager communication preferences go to `ai/context/people/manager.md`
- role-to-person mapping and recurring stakeholders go to `ai/context/people/`
- confirmed decisions go to `ai/context/decisions/`
- behavioral rules for how this workspace should respond go to the exact command, prompt, agent, skill, or knowledge file that enforces that behavior
- Default to writing new same-day information to today's log unless a more durable destination is clearly better.
- Update preexisting memory when a new prompt clarifies or corrects something already stored.
- Do not wait for a dedicated sync command if the correct memory update is already obvious.
- Do not leave behavior-only corrections only in daily logs. If a correction should affect future output, update the tool or instruction that produces that output.
- Do not over-promote uncertain information. Keep uncertain items in the daily log.
- When drafting communication, preserve technical meaning and improve clarity in natural US English.
- When answering Swift/iOS programming questions, use the project-local iOS skills and `ai/context/ios/`.

View File

@@ -15,6 +15,7 @@ Use these files as the baseline context:
@ai/context/ios/project-swift-guidance.md
@ai/context/systems/index.md
@ai/context/workstreams/index.md
@ai/context/workstreams/flow-page-references.md
@ai/context/process/communication.md
@ai/context/process/ai-to-ai-prompting.md
@ai/context/process/jira-story-rules.md

View File

@@ -11,6 +11,7 @@ Read:
@ai/context/project.md
@ai/context/systems/index.md
@ai/context/workstreams/index.md
@ai/context/workstreams/flow-page-references.md
@ai/context/process/index.md
@ai/work-items/index.md
@ai/state/current.md
@@ -49,8 +50,14 @@ Instructions:
- `ai/context/workstreams/*.md`
- `ai/context/process/*.md`
- `ai/context/decisions/*.md`
- `.opencode/commands/*.md` when command behavior needs to change
- `prompts/*.md` when a reusable output template needs to change
- `.opencode/agents/*.md` or `ai/AGENTS.md` when default agent behavior needs to change
- `.opencode/skills/*/SKILL.md` when a specialized workflow needs to change
- `knowledge/*.md` when a durable workspace rule needs to change
- Prefer concrete project updates over broad summaries
- If a fact is still ambiguous, do not promote it
- If the promoted fact is a reusable behavior correction, do not leave it only in a daily log; update the operational file that controls future behavior
- Use this command when you want a deliberate manual pass beyond the agent's default automatic memory maintenance
Return:

View File

@@ -15,6 +15,7 @@ Read:
@ai/context/index.md
@ai/context/project.md
@ai/context/workstreams/index.md
@ai/context/workstreams/flow-page-references.md
@ai/context/process/communication.md
@ai/context/process/jira-story-rules.md
@ai/context/people/manager.md
@@ -49,6 +50,8 @@ Before drafting:
- prioritize story-based updates over side questions, memory refreshes, or manager-only context
- if documentation or root cause updates directly support a story, roll them into that story's update instead of listing them separately
- exclude items that are not directly tied to a story unless they are true blockers
- when one Jira item has multiple concrete updates, group them under one top-level `JIRA-ID - Title` bullet with indented markdown sub-bullets instead of repeating the same Jira line
- use `ai/context/workstreams/flow-page-references.md` to preserve real flow/page identifiers when shorthand appears in logs or messages
Return a standup that is:
@@ -61,4 +64,5 @@ Return a standup that is:
- free of any mention of Jeff by name
- free of any mention of Mattermost, since it is internal-only communication
- uses bullet points for each item
- groups multiple updates for the same Jira item as indented sub-bullets
- uses `JIRA-ID - Title` or `JIRA-ID Title` formatting instead of comma-separated ID/title formatting

View File

@@ -12,6 +12,7 @@ Read:
@ai/context/project.md
@ai/context/systems/index.md
@ai/context/workstreams/index.md
@ai/context/workstreams/flow-page-references.md
@ai/context/process/context-maintenance.md
@ai/context/people/manager.md
@ai/context/people/index.md
@@ -46,8 +47,14 @@ Instructions:
- `ai/context/people/index.md`
- `ai/context/people/*.md`
- `ai/context/decisions/`
- `.opencode/commands/*.md`
- `prompts/*.md`
- `.opencode/agents/*.md`
- `.opencode/skills/*/SKILL.md`
- `knowledge/*.md`
- Update the appropriate files directly
- If an existing statement became stale, replace or refine it
- If the new information changes how this workspace should behave, update the linked command, prompt, agent, skill, or knowledge file that enforces that behavior
- Do not invent missing facts
- Keep uncertain information in the daily log instead of promoting it to stable context
- Do not ask for promotion confirmation when the correct destination is already clear