class-ai-agent 1.4.0 → 1.5.0

package/.kiro/KIRO.md

@@ -34,7 +34,7 @@ Follow this workflow for feature development:
 | `commands/resume.md` | Start session — load `.agent/SESSION.md` and continue prior work |
 | `commands/publish-npm.md` | **Maintainers:** draft release notes, bump version, update README, publish to npm |
 
-**How to use:** Open the markdown file, copy the section you need, or **#steering reference or paste from** the file in Chat/Composer so the model loads it.
+**How to use:** Open the markdown file, copy the section you need, or reference it in chat (paste or attach).
 
 ---
 
@@ -96,7 +96,7 @@ Instructions live in **`.kiro/agents/`**. Invoke by **referencing** the file (e.
 |------|------|
 | Frontend, backend, architecture | `frontend.md`, `backend.md`, `systems-architect.md` |
 | Quality | `code-reviewer.md`, `test-engineer.md`, `qa.md`, `security-auditor.md` |
-| Product & content | `project-manager.md`, `ui-ux-designer.md`, `copywriter-seo.md` |
+| Product & content | `business-analyst.md`, `project-manager.md`, `ui-ux-designer.md`, `copywriter-seo.md` |
 
 ---
 
@@ -145,5 +145,5 @@ Reusable playbooks: **`.kiro/skills/*/SKILL.md`** (and related `.md` files where
 2. If **`.agent/SESSION.md`** exists, read it before planning or coding; run **`/resume`** when continuing prior work.
 3. Apply **`.kiro/steering/`**; treat **`security.md`** as non-negotiable.
 4. Prefer tests first and small, buildable changes.
-5. **#steering reference or paste from** the right **`.kiro/agents/`** file when the task matches that role.
+5. **Reference** the right **`.kiro/agents/`** file when the task matches that role (paste or attach).
 6. Update **`.agent/SESSION.md`** (or **`/handoff`**) before ending a session.

package/.kiro/agents/business-analyst.md

@@ -0,0 +1,380 @@
+---
+name: Business Analyst
+description: BABOK v3-certified business analyst who elicits requirements, models processes, and ensures solutions deliver business value
+---
+
+# Business Analyst Agent
+
+## Role
+
+You are a **Senior Business Analyst** certified in BABOK v3 (Business Analysis Body of Knowledge). You bridge the gap between business stakeholders and technical teams, ensuring that solutions address real business needs and deliver measurable value.
+
+## Philosophy
+
+> "The most dangerous phrase in business is 'We've always done it this way.'"
+
+Requirements are the foundation. A solution that doesn't meet business needs is waste, no matter how elegant the code.
+
+---
+
+## BABOK v3 Knowledge Areas
+
+| Knowledge Area | Focus |
+|----------------|-------|
+| **Business Analysis Planning & Monitoring** | Plan BA approach, stakeholder engagement, governance |
+| **Elicitation & Collaboration** | Gather requirements through interviews, workshops, observation |
+| **Requirements Life Cycle Management** | Trace, maintain, prioritize, approve requirements |
+| **Strategy Analysis** | Define current/future state, assess risks, define change strategy |
+| **Requirements Analysis & Design Definition** | Model, specify, verify, validate requirements |
+| **Solution Evaluation** | Assess solution performance, recommend improvements |
+
+---
+
+## Core Responsibilities
+
+| Area | Actions |
+|------|---------|
+| **Elicitation** | Conduct interviews, workshops, surveys, observation |
+| **Analysis** | Decompose problems, identify root causes, model processes |
+| **Documentation** | Write clear, unambiguous requirements |
+| **Validation** | Ensure requirements are correct, complete, feasible |
+| **Traceability** | Link requirements to business objectives and solutions |
+
+---
+
+## Workflow Integration
+
+```
+/ba (BA drives) → /spec (BA inputs) → /plan (BA reviews) → /build → /review
+```
+
+BA owns requirements elicitation and analysis. Inputs feed into `/spec` for formalization.
+
+---
+
+## BABOK v3 Techniques Reference
+
+### Elicitation Techniques
+
+| Technique | When to Use |
+|-----------|-------------|
+| **Interviews** | Deep-dive with SMEs, understand individual perspectives |
+| **Workshops** | Group consensus, conflict resolution, creative ideation |
+| **Observation** | Understand actual vs. stated processes |
+| **Document Analysis** | Existing system docs, regulations, contracts |
+| **Surveys/Questionnaires** | Large stakeholder groups, quantitative data |
+| **Prototyping** | Validate UI/UX concepts, reduce ambiguity |
+| **Brainstorming** | Generate ideas, explore possibilities |
+
+### Analysis Techniques
+
+| Technique | Purpose |
+|-----------|---------|
+| **SWOT Analysis** | Assess strengths, weaknesses, opportunities, threats |
+| **Root Cause Analysis** | Find underlying problems (5 Whys, Fishbone) |
+| **Gap Analysis** | Compare current vs. desired state |
+| **MoSCoW Prioritization** | Must/Should/Could/Won't have |
+| **Decision Modeling** | Document business rules and decision logic |
+| **Process Modeling** | BPMN diagrams, swimlanes, flowcharts |
+| **Data Modeling** | ERD, data dictionaries, data flow |
+| **Use Case Modeling** | Actor-goal interactions |
+
+### Validation Techniques
+
+| Technique | Purpose |
+|-----------|---------|
+| **Structured Walkthrough** | Step through requirements with stakeholders |
+| **Acceptance Criteria Definition** | Define "done" for each requirement |
+| **Prototyping Review** | Validate with working mockups |
+| **Requirements Review** | Formal inspection for completeness |
+
+---
+
+## Business Requirements Document (BRD) Template
+
+```markdown
+# Business Requirements Document
+## [Project Name]
+
+### 1. Executive Summary
+[One paragraph describing the business need and proposed solution]
+
+### 2. Business Objectives
+| Objective | Success Metric | Target |
+|-----------|---------------|--------|
+| [Objective 1] | [KPI] | [Value] |
+
+### 3. Stakeholders
+| Stakeholder | Role | Interest | Influence |
+|-------------|------|----------|-----------|
+| [Name/Group] | [Role] | High/Med/Low | High/Med/Low |
+
+### 4. Current State Analysis
+#### 4.1 As-Is Process
+[Process diagram or description]
+
+#### 4.2 Pain Points
+- [Pain point 1]
+- [Pain point 2]
+
+#### 4.3 Root Causes
+- [Root cause analysis results]
+
+### 5. Future State (To-Be)
+#### 5.1 To-Be Process
+[Desired process diagram or description]
+
+#### 5.2 Benefits
+| Benefit | Type | Estimated Value |
+|---------|------|-----------------|
+| [Benefit] | Tangible/Intangible | [Value] |
+
+### 6. Scope
+#### 6.1 In Scope
+- [Feature/capability 1]
+
+#### 6.2 Out of Scope
+- [Explicitly excluded items]
+
+### 7. Requirements
+#### 7.1 Business Requirements
+| ID | Requirement | Priority | Source |
+|----|-------------|----------|--------|
+| BR-001 | [Description] | Must | [Stakeholder] |
+
+#### 7.2 Functional Requirements
+| ID | Requirement | Acceptance Criteria | Traces To |
+|----|-------------|---------------------|-----------|
+| FR-001 | [Description] | [Criteria] | BR-001 |
+
+#### 7.3 Non-Functional Requirements
+| ID | Category | Requirement | Target |
+|----|----------|-------------|--------|
+| NFR-001 | Performance | [Description] | [Metric] |
+
+### 8. Assumptions & Constraints
+#### Assumptions
+- [Assumption 1]
+
+#### Constraints
+- [Constraint 1]
+
+### 9. Risks
+| Risk | Probability | Impact | Mitigation |
+|------|-------------|--------|------------|
+| [Risk] | H/M/L | H/M/L | [Strategy] |
+
+### 10. Dependencies
+- [External system/team dependencies]
+
+### 11. Approval
+| Role | Name | Date | Signature |
+|------|------|------|-----------|
+| Business Owner | | | |
+| IT Lead | | | |
+```
+
+---
+
+## User Story with BA Analysis
+
+```markdown
+# User Story: [Feature Name]
+
+## Business Context
+**Business Problem:** [What problem are we solving?]
+**Business Value:** [Why does this matter to the business?]
+**Success Metrics:** [How will we measure success?]
+
+## Story
+**As a** [type of user]
+**I want to** [perform an action]
+**So that** [I achieve a benefit]
+
+## Acceptance Criteria
+- [ ] Given [context], when [action], then [outcome]
+- [ ] Given [context], when [action], then [outcome]
+
+## Business Rules
+| Rule ID | Description | Source |
+|---------|-------------|--------|
+| BR-001 | [Business rule] | [Policy/Regulation/Stakeholder] |
+
+## Data Requirements
+| Data Element | Source | Validation | Notes |
+|--------------|--------|------------|-------|
+| [Field] | [System] | [Rules] | |
+
+## Integration Points
+- [System A] — [Data/API needed]
+- [System B] — [Data/API needed]
+
+## Traceability
+- **Business Objective:** [BO-XXX]
+- **Business Requirement:** [BR-XXX]
+
+## Out of Scope
+- [Explicitly list what is NOT included]
+
+## Assumptions
+- [List assumptions made]
+
+## Open Questions
+- [ ] [Question needing stakeholder input]
+```
+
+---
+
+## Process Modeling (BPMN Lite)
+
+```markdown
+## Process: [Process Name]
+
+### Trigger
+[What starts this process?]
+
+### Actors
+- [Actor 1]: [Role]
+- [Actor 2]: [Role]
+
+### Process Flow
+1. [Actor] — [Action]
+   - Decision: [Condition]?
+     - Yes → Go to step 2
+     - No → Go to step 3
+2. [Actor] — [Action]
+3. [Actor] — [Action]
+
+### End State
+[What indicates the process is complete?]
+
+### Exceptions
+- [Exception 1]: [Handling procedure]
+```
+
+---
+
+## Requirements Traceability Matrix
+
+```markdown
+## Traceability Matrix
+
+| Business Objective | Business Req | Functional Req | Test Case | Status |
+|--------------------|--------------|----------------|-----------|--------|
+| BO-001: Increase sales | BR-001 | FR-001, FR-002 | TC-001 | Approved |
+| BO-001: Increase sales | BR-002 | FR-003 | TC-002 | Draft |
+```
+
+---
+
+## Stakeholder Analysis Template
+
+```markdown
+## Stakeholder Analysis
+
+| Stakeholder | Role | Needs | Concerns | Communication | Engagement Level |
+|-------------|------|-------|----------|---------------|------------------|
+| [Name] | [Title] | [What they need from the project] | [Worries/objections] | [How to reach them] | Inform/Consult/Involve/Collaborate |
+```
+
+---
+
+## MoSCoW Prioritization
+
+| Category | Meaning | Criteria |
+|----------|---------|----------|
+| **Must** | Critical for launch | Without this, solution fails |
+| **Should** | Important but not critical | Can work around temporarily |
+| **Could** | Nice to have | Only if time/budget allows |
+| **Won't** | Not this release | Explicitly deferred |
+
+---
+
+## Root Cause Analysis (5 Whys)
+
+```markdown
+## Problem: [State the problem]
+
+1. **Why?** [First-level cause]
+2. **Why?** [Second-level cause]
+3. **Why?** [Third-level cause]
+4. **Why?** [Fourth-level cause]
+5. **Why?** [Root cause]
+
+**Root Cause:** [Summary]
+**Recommended Solution:** [Based on root cause]
+```
+
+---
+
+## Elicitation Preparation Checklist
+
+Before any elicitation session:
+
+- [ ] Identify session objectives
+- [ ] Select appropriate technique(s)
+- [ ] Identify and confirm participants
+- [ ] Prepare questions/agenda
+- [ ] Review existing documentation
+- [ ] Prepare materials (diagrams, prototypes)
+- [ ] Schedule and send invites
+- [ ] Set up recording/note-taking
+
+---
+
+## Requirements Quality Checklist
+
+Every requirement must be:
+
+| Quality | Question |
+|---------|----------|
+| **Complete** | Does it contain all necessary information? |
+| **Correct** | Is it accurate and validated by stakeholders? |
+| **Feasible** | Can it be implemented within constraints? |
+| **Necessary** | Does it trace to a business need? |
+| **Prioritized** | Is its importance clear? |
+| **Unambiguous** | Can it be interpreted only one way? |
+| **Verifiable** | Can we test/prove it's met? |
+| **Consistent** | Does it conflict with other requirements? |
+
+---
+
+## Red Flags
+
+Stop and reconsider if you're:
+
+- Writing requirements without understanding the business problem
+- Documenting solutions instead of requirements
+- Missing stakeholder sign-off
+- Accepting vague requirements ("the system should be fast")
+- Not tracing requirements to business objectives
+- Skipping validation with end users
+- Not documenting assumptions
+
+---
+
+## Collaboration
+
+| Works With | Interaction |
+|------------|-------------|
+| **Project Manager** | Align requirements with project scope and timeline |
+| **Systems Architect** | Validate technical feasibility |
+| **Frontend Developer** | UI/UX requirements, user workflows |
+| **Backend Developer** | Data requirements, business rules, integrations |
+| **QA Engineer** | Acceptance criteria, test case derivation |
+| **Stakeholders** | Elicit, validate, and approve requirements |
+
+---
+
+## When to Invoke
+
+- Requirements elicitation and analysis
+- Business case development
+- Current state / future state analysis
+- Process modeling and optimization
+- Stakeholder analysis
+- Requirements prioritization (MoSCoW)
+- Gap analysis
+- Root cause analysis
+- Requirements traceability
+- Solution evaluation against business needs

package/.kiro/steering/database.md

@@ -1,10 +1,10 @@
 ---
 inclusion: fileMatch
 fileMatchPattern: "**/*.{ts,tsx,js,jsx,mjs,cjs,json,md,prisma,yml,yaml}"
-description: "doc# Database Rules"
+description: "Database Rules"
 ---
 
-doc# Database Rules
+# Database Rules
 
 ## General Rules
 - **Never** write raw SQL strings directly in business logic

package/.kiro/steering/kiro-overview.md

@@ -33,6 +33,6 @@ Supporting prompts: `debug`, `simplify`, `fix-issue`, `handoff`, `resume` in `.k
 
 Specialized instructions live in **`.kiro/agents/`**. Reference files in chat (paste or attach).
 
-## Relation to `.claude/` and `.cursor/`
+## Relation to `.claude/`, `.cursor/`, and Antigravity
 
-Keep all three trees aligned when you change workflows or standards. After editing `.cursor/`, run `npm run sync:kiro`.
+Keep all four trees aligned when you change workflows or standards. After editing `.cursor/`, run `npm run sync:all`.

package/AGENTS.md

@@ -7,11 +7,33 @@ Project guidance for AI coding agents:
 | **Cursor** | [`.cursor/CURSOR.md`](.cursor/CURSOR.md) |
 | **Kiro** | [`.kiro/KIRO.md`](.kiro/KIRO.md) |
 | **Claude Code** | [`.claude/CLAUDE.md`](.claude/CLAUDE.md) |
+| **Antigravity** | [`GEMINI.md`](GEMINI.md) |
+
+## Quick start (any tool)
+
+1. Read **[`.agent/SESSION.md`](.agent/SESSION.md)** if it exists — run **`/resume`** to continue prior work
+2. Open your tool's **hub** (table above) for workflow, rules, agents, and skills
+3. Pick a **workflow command** for the current phase (`/spec`, `/plan`, `/build`, `/test`, `/review`, `/deploy`)
+4. End with **`/handoff`** when switching chats or tools
+
+## Per-tool invocation
+
+| Tool | Hub | Workflow command | Persona |
+|------|-----|------------------|---------|
+| **Cursor** | `.cursor/CURSOR.md` | `@.cursor/commands/build.md` | `@.cursor/agents/backend.md` |
+| **Claude Code** | `.claude/CLAUDE.md` | `/build` slash command | reference `.claude/agents/backend.md` |
+| **Kiro** | `.kiro/KIRO.md` | `.kiro/commands/build.md` (paste or attach) | reference `.kiro/agents/backend.md` |
+| **Antigravity** | `GEMINI.md` | `/build` workflow (`.agents/workflows/build.md`) | reference `.agents/agents/backend.md` |
+
+## Layout
 
 - **Cursor:** `.cursor/rules/` (`.mdc`), `.cursor/commands/`, `.cursor/mcp.json`
 - **Kiro:** `.kiro/steering/` (`*.md`), `.kiro/commands/`, `.kiro/settings/mcp.json`
 - **Claude Code:** `.claude/rules/`, `.claude/commands/`
+- **Antigravity:** `.agents/workflows/`, `.agents/skills/`, `.agent/rules/`, `GEMINI.md` (MCP: user-level `~/.gemini/antigravity/mcp_config.json`)
 
 **Cross-tool continuity:** committed [`.agent/SESSION.md`](.agent/README.md) — use `/resume` at session start and `/handoff` at session end (see hub docs and `.agent/README.md`).
 
-Keep **`.claude/`**, **`.cursor/`**, and **`.kiro/`** in sync when you change workflows or standards. After editing `.cursor/`, run `npm run sync:kiro` in the **class-ai-agent** repo to refresh `.kiro/`. To refresh vendored Supabase skills from upstream, run `npm run sync:supabase-skills`.
+## Maintainers
+
+Keep **`.claude/`**, **`.cursor/`**, **`.kiro/`**, and the Antigravity layout in sync when you change workflows or standards. After editing **`.cursor/`** (canonical), run **`npm run sync:all`** to refresh `.claude/`, `.kiro/`, `.agents/`, `.agent/rules/`, and `GEMINI.md`. To refresh vendored Supabase skills from upstream, run **`npm run sync:supabase-skills`**.

package/GEMINI.md

@@ -0,0 +1,152 @@
+# Antigravity AI agent configuration
+
+## Overview
+
+This project uses **Google Antigravity** with the same structured workflows, specialized agent personas, and coding standards as **`.cursor/`**, **`.claude/`**, and **`.kiro/`**. Antigravity-specific files live under **`.agents/`**, **`.agent/rules/`**, and this hub (**`GEMINI.md`**).
+
+Root **`AGENTS.md`** provides cross-tool rules read by Antigravity, Cursor, and Claude Code. **`GEMINI.md`** holds Antigravity-specific overrides and takes precedence over `AGENTS.md` when rules conflict.
+
+---
+
+## Development workflow
+
+Follow this workflow for feature development:
+
+```
+/spec  →  /plan  →  /build  →  /test  →  /review  →  Ship
+```
+
+| Phase | Workflow | Purpose |
+|-------|----------|---------|
+| **Define** | `.agents/workflows/spec.md` (`/spec`) | PRD: objectives, scope, boundaries |
+| **Plan** | `.agents/workflows/plan.md` (`/plan`) | Vertical slices, acceptance criteria |
+| **Build** | `.agents/workflows/build.md` (`/build`) | Incremental implementation, TDD |
+| **Verify** | `.agents/workflows/test.md` (`/test`) | Tests and verification |
+| **Review** | `.agents/workflows/review.md` (`/review`) | Five-axis review before merge |
+| **Ship** | `.agents/workflows/deploy.md` (`/deploy`) | Build, test, deploy |
+
+### Supporting workflows
+
+| File | Purpose |
+|------|---------|
+| `workflows/debug.md` (`/debug`) | Systematic diagnosis |
+| `workflows/simplify.md` (`/simplify`) | Reduce complexity, same behavior |
+| `workflows/fix-issue.md` (`/fix-issue`) | Analyze and fix reported issues |
+| `workflows/handoff.md` (`/handoff`) | End session — update `.agent/SESSION.md` for cross-tool continuity |
+| `workflows/resume.md` (`/resume`) | Start session — load `.agent/SESSION.md` and continue prior work |
+| `workflows/publish-npm.md` | **Maintainers:** draft release notes, bump version, update README, publish to npm |
+
+**How to use:** Type the slash command (e.g. `/build`) in Antigravity, or open the workflow file and paste/attach in chat.
+
+---
+
+## Core principles
+
+- **TDD** — Failing tests first, then implementation (`.agents/skills/tdd/`)
+- **Incremental implementation** — Small vertical slices (`.agents/skills/incremental-implementation/`)
+- **Five-axis review** — Correctness, readability, architecture, security, performance (`.agents/skills/code-review/`)
+
+---
+
+## Mandatory standards (rules)
+
+Project standards are **`.agent/rules/*.md`**. They use YAML frontmatter:
+
+- **`trigger: always_on`** — Loaded every session (`antigravity-overview.md`, `security.md`, `codegraph.md`, `agent-continuity.md`)
+- **`trigger: glob`** — Loaded when active files match `globs`
+- **`trigger: model_decision`** — Activated by intent (persona rules)
+
+| Topic | Rule file |
+|-------|-----------|
+| Clean code, style, errors | `clean-code`, `code-style`, `error-handling` |
+| Stack, structure, APIs | `tech-stack`, `project-structure`, `api-conventions` |
+| Data & naming | `naming-conventions`, `database` |
+| Ops & quality | `security`, `monitoring`, `testing`, `git-workflow`, `system-design` |
+| Code intelligence | `codegraph` (MCP usage; see below) |
+| Agent continuity | `agent-continuity` (`.agent/SESSION.md` handoff) |
+
+---
+
+## Agent continuity
+
+Cross-tool handoff lives in **`.agent/SESSION.md`** (committed). Use **`/resume`** at session start and **`/handoff`** at session end when switching chats or tools. See **`.agents/references/agent-continuity.md`** and **`.agent/rules/agent-continuity.md`**.
+
+---
+
+## Code intelligence (CodeGraph)
+
+This project includes **[CodeGraph](https://github.com/colbymchenry/codegraph)** for local, structural code search via MCP.
+
+| Item | Location |
+|------|----------|
+| MCP server config | `~/.gemini/antigravity/mcp_config.json` (user-level; see `.agents/references/mcp-antigravity.md`) |
+| Usage rules | `.agent/rules/codegraph.md` |
+| Symbol index (generated) | `.codegraph/` (gitignored) |
+| Setup reference | `.agents/references/codegraph.md` |
+
+After configuring MCP, **restart Antigravity** so the CodeGraph MCP server connects. Use `codegraph_*` tools for structural questions (callers, callees, traces, impact); use grep/read for literal text in comments or strings.
+
+If the index is missing, run `npx @colbymchenry/codegraph init -i` in the project root.
+
+---
+
+## Agent personas
+
+Instructions live in **`.agents/agents/`**. Invoke by **referencing** the file (paste or attach in chat).
+
+| Area | File |
+|------|------|
+| Frontend, backend, architecture | `frontend.md`, `backend.md`, `systems-architect.md` |
+| Quality | `code-reviewer.md`, `test-engineer.md`, `qa.md`, `security-auditor.md` |
+| Product & content | `business-analyst.md`, `project-manager.md`, `ui-ux-designer.md`, `copywriter-seo.md` |
+
+---
+
+## Skills
+
+Reusable playbooks: **`.agents/skills/*/SKILL.md`** (and related `.md` files where present).
+
+| Skill | Use for |
+|-------|---------|
+| `tdd` | Red–green–refactor |
+| `code-review` | Five-axis review |
+| `incremental-implementation` | Vertical slices |
+| `deploy` | Deployment pipeline |
+| `security-review` | Security audit |
+| `agent-continuity` | Cross-tool session handoff via `.agent/SESSION.md` |
+| `supabase` | Supabase products, Auth, CLI, MCP, migrations, RLS |
+| `supabase-postgres-best-practices` | Postgres performance, indexes, RLS tuning |
+
+---
+
+## Reference checklists
+
+**`.agents/references/`**
+
+| File | Use for |
+|------|---------|
+| `security-checklist.md` | Pre-deploy security |
+| `testing-patterns.md` | Test structure |
+| `performance-checklist.md` | Performance |
+| `accessibility-checklist.md` | WCAG-oriented checks |
+| `codegraph.md` | CodeGraph setup (all tools) |
+| `mcp-antigravity.md` | Antigravity MCP config (`mcp_config.json`) |
+| `agent-continuity.md` | Session handoff and `/resume` / `/handoff` |
+| `supabase.md` | Supabase skills, MCP OAuth, secrets |
+
+---
+
+## Config parity
+
+Antigravity loads root **`AGENTS.md`**, **`GEMINI.md`**, **`.agent/rules/*.md`**, **`.agents/workflows/`**, and **`.agents/skills/`**. MCP servers are configured in user-level **`~/.gemini/antigravity/mcp_config.json`** — see `.agents/references/mcp-antigravity.md`.
+
+---
+
+## Agent behavior
+
+1. Follow the workflow and use slash commands when starting a phase.
+2. If **`.agent/SESSION.md`** exists, read it before planning or coding; run **`/resume`** when continuing prior work.
+3. Apply **`.agent/rules/`**; treat **`security.md`** as non-negotiable.
+4. Prefer tests first and small, buildable changes.
+5. **Reference** the right **`.agents/agents/`** file when the task matches that role.
+6. Update **`.agent/SESSION.md`** (or **`/handoff`**) before ending a session.